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

27 files changed, 128 insertions, 104 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 20d1465a2ab..4518dc50090 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -144,7 +144,6 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 
 #else /* !CONFIG_ACPI */
 
-#define acpi_disabled 1
 #define acpi_lapic 0
 #define acpi_ioapic 0
 static inline void acpi_noirq_set(void) { }
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index ac95995b7ba..4b180897e6b 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -31,6 +31,7 @@ extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_shutdown(void);
+extern void amd_iommu_apply_erratum_63(u16 devid);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c6d21b18806..474d80d3e6c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -66,6 +66,19 @@ static inline void default_inquire_remote_apic(int apicid)
 }
 
 /*
+ * With 82489DX we can't rely on apic feature bit
+ * retrieved via cpuid but still have to deal with
+ * such an apic chip so we assume that SMP configuration
+ * is found from MP table (64bit case uses ACPI mostly
+ * which set smp presence flag as well so we are safe
+ * to use this helper too).
+ */
+static inline bool apic_from_smp_config(void)
+{
+	return smp_found_config && !disable_apic;
+}
+
+/*
  * Basic functions accessing APICs.
  */
 #ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 5d367caa0e3..549860d3be8 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_CACHE_H
 #define _ASM_X86_CACHE_H
 
+#include <linux/linkage.h>
+
 /* L1 cache line size */
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
@@ -13,7 +15,7 @@
 #ifdef CONFIG_SMP
 #define __cacheline_aligned_in_smp					\
 	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))	\
-	__attribute__((__section__(".data.page_aligned")))
+	__page_aligned_data
 #endif
 #endif
 
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 7c5ef8b14d9..46fc474fd81 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -161,7 +161,8 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	    "adcl $0, %0	;\n"
 	    : "=&r" (sum)
 	    : "r" (saddr), "r" (daddr),
-	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum));
+	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)
+	    : "memory");
 
 	return csum_fold(sum);
 }
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 82ceb788a98..ee1931be659 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -312,19 +312,23 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
 
 extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
 
-#define cmpxchg64(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 4))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg64((ptr),		\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	__ret;								\
-})
+#define cmpxchg64(ptr, o, n)					\
+({								\
+	__typeof__(*(ptr)) __ret;				\
+	__typeof__(*(ptr)) __old = (o);				\
+	__typeof__(*(ptr)) __new = (n);				\
+	alternative_io("call cmpxchg8b_emu",			\
+			"lock; cmpxchg8b (%%esi)" ,		\
+		       X86_FEATURE_CX8,				\
+		       "=A" (__ret),				\
+		       "S" ((ptr)), "0" (__old),		\
+		       "b" ((unsigned int)__new),		\
+		       "c" ((unsigned int)(__new>>32))		\
+		       : "memory");				\
+	__ret; })
+
+
+
 #define cmpxchg64_local(ptr, o, n)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index e8de2f6f5ca..617bd56b307 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -288,7 +288,7 @@ static inline void load_LDT(mm_context_t *pc)
 
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
-	return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
+	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
 }
 
 static inline void set_desc_base(struct desc_struct *desc, unsigned long base)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0ee770d23d0..6a25d5d4283 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -14,6 +14,12 @@
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifdef CONFIG_ISA
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
+#else
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
+#endif
+
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
@@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
-	if (!dev) {
+	if (!dev)
 		dev = &x86_dma_fallback_dev;
-		gfp |= GFP_DMA;
-	}
 
 	if (!is_device_dma_capable(dev))
 		return NULL;
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 5e3f2044f0d..f5693c81a1d 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -49,7 +49,7 @@ BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
 BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
 #endif
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3be000435fa..d83892226f7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -796,6 +796,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b608a64c581..f1363b72364 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -133,6 +133,8 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
+extern void (*x86_mce_decode_callback)(struct mce *m);
+
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index f923203dc39..4a2d4e0c18d 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -37,12 +37,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	if (likely(prev != next)) {
 		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 #ifdef CONFIG_SMP
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
-		cpu_set(cpu, next->cpu_vm_mask);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 
 		/* Re-load page tables */
 		load_cr3(next->pgd);
@@ -58,7 +58,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
 			/* We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index e63cf7d441e..139d4c1a33a 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -40,8 +40,7 @@ extern unsigned int nmi_watchdog;
 #define NMI_INVALID	3
 
 struct ctl_table;
-struct file;
-extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041..efb38994859 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -840,42 +840,22 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
 
 static inline unsigned long __raw_local_save_flags(void)
 {
-	unsigned long f;
-
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : paravirt_type(pv_irq_ops.save_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
-	return f;
+	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : PV_FLAGS_ARG(f),
-		       paravirt_type(pv_irq_ops.restore_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
+	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
 static inline void raw_local_irq_disable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_disable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
 static inline void raw_local_irq_enable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_enable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
 static inline unsigned long __raw_local_irq_save(void)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index dd0f5b32489..9357473c8da 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -494,10 +494,11 @@ int paravirt_disable_iospace(void);
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
+/* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS					\
 	unsigned long __edi = __edi, __esi = __esi,	\
-		__edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
+		__edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
@@ -509,6 +510,7 @@ int paravirt_disable_iospace(void);
 				"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+/* void functions are still allowed [re]ax for scratch */
 #define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
 #define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
 
@@ -583,8 +585,8 @@ int paravirt_disable_iospace(void);
 		       VEXTRA_CLOBBERS,					\
 		       pre, post, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)			\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
+	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
 		      PVOP_VCALLEE_CLOBBERS, ,				\
 		      pre, post, ##__VA_ARGS__)
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index f76a162c082..ada8c201d51 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -143,7 +143,11 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 static inline const struct cpumask *
 cpumask_of_pcibus(const struct pci_bus *bus)
 {
-	return cpumask_of_node(__pcibus_to_node(bus));
+	int node;
+
+	node = __pcibus_to_node(bus);
+	return (node == -1) ? cpu_online_mask :
+			      cpumask_of_node(node);
 }
 #endif
 
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_event.h
index e7b7c938ae2..ad7ce3fd506 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -1,8 +1,8 @@
-#ifndef _ASM_X86_PERF_COUNTER_H
-#define _ASM_X86_PERF_COUNTER_H
+#ifndef _ASM_X86_PERF_EVENT_H
+#define _ASM_X86_PERF_EVENT_H
 
 /*
- * Performance counter hw details:
+ * Performance event hw details:
  */
 
 #define X86_PMC_MAX_GENERIC					8
@@ -43,7 +43,7 @@
 union cpuid10_eax {
 	struct {
 		unsigned int version_id:8;
-		unsigned int num_counters:8;
+		unsigned int num_events:8;
 		unsigned int bit_width:8;
 		unsigned int mask_length:8;
 	} split;
@@ -52,7 +52,7 @@ union cpuid10_eax {
 
 union cpuid10_edx {
 	struct {
-		unsigned int num_counters_fixed:4;
+		unsigned int num_events_fixed:4;
 		unsigned int reserved:28;
 	} split;
 	unsigned int full;
@@ -60,7 +60,7 @@ union cpuid10_edx {
 
 
 /*
- * Fixed-purpose performance counters:
+ * Fixed-purpose performance events:
  */
 
 /*
@@ -87,22 +87,22 @@ union cpuid10_edx {
 /*
  * We model BTS tracing as another fixed-mode PMC.
  *
- * We choose a value in the middle of the fixed counter range, since lower
- * values are used by actual fixed counters and higher values are used
+ * We choose a value in the middle of the fixed event range, since lower
+ * values are used by actual fixed events and higher values are used
  * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
  */
 #define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
 
 
-#ifdef CONFIG_PERF_COUNTERS
-extern void init_hw_perf_counters(void);
-extern void perf_counters_lapic_init(void);
+#ifdef CONFIG_PERF_EVENTS
+extern void init_hw_perf_events(void);
+extern void perf_events_lapic_init(void);
 
-#define PERF_COUNTER_INDEX_OFFSET			0
+#define PERF_EVENT_INDEX_OFFSET			0
 
 #else
-static inline void init_hw_perf_counters(void)		{ }
-static inline void perf_counters_lapic_init(void)	{ }
+static inline void init_hw_perf_events(void)		{ }
+static inline void perf_events_lapic_init(void)	{ }
 #endif
 
-#endif /* _ASM_X86_PERF_COUNTER_H */
+#endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7b467bf3c68..d1f4a760be2 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -277,6 +277,7 @@ static inline pteval_t pte_flags(pte_t pte)
 typedef struct page *pgtable_t;
 
 extern pteval_t __supported_pte_mask;
+extern void set_nx(void);
 extern int nx_enabled;
 
 #define pgprot_writecombine	pgprot_writecombine
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c3429e8b242..c9786480f0f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -1000,7 +1000,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
-#define KSTK_ESP(tsk)		-1 /* sorry. doesn't work for syscall. */
+extern unsigned long KSTK_ESP(struct task_struct *task);
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 6a84ed166ae..1e796782cd7 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -121,7 +121,6 @@ static inline void arch_send_call_function_single_ipi(int cpu)
 	smp_ops.send_call_func_single_ipi(cpu);
 }
 
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	smp_ops.send_call_func_ipi(mask);
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index c86f452256d..ae907e61718 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -65,7 +65,6 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 	case 4:
 		*(int *)to = *(int *)from;
 		return to;
-
 	case 3:
 		*(short *)to = *(short *)from;
 		*((char *)to + 2) = *((char *)from + 2);
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d82f39bb790..8d33bc5462d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -1,7 +1,7 @@
 /*
  * Access to user system call parameters and results
  *
- * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2008-2009 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -16,13 +16,13 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 
-static inline long syscall_get_nr(struct task_struct *task,
-				  struct pt_regs *regs)
+/*
+ * Only the low 32 bits of orig_ax are meaningful, so we return int.
+ * This importantly ignores the high bits on 64-bit, so comparisons
+ * sign-extend the low 32 bits.
+ */
+static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	/*
-	 * We always sign-extend a -1 value being set here,
-	 * so this is always either -1L or a syscall number.
-	 */
 	return regs->orig_ax;
 }
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 6f0695d744b..40e37b10c6c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ extern unsigned long node_remap_size[];
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_POWERSAVINGS_BALANCE		\
 				| 0*SD_SHARE_PKG_RESOURCES		\
@@ -165,21 +166,11 @@ static inline int numa_node_id(void)
 	return 0;
 }
 
-static inline int cpu_to_node(int cpu)
-{
-	return 0;
-}
-
 static inline int early_cpu_to_node(int cpu)
 {
 	return 0;
 }
 
-static inline const struct cpumask *cpumask_of_node(int node)
-{
-	return cpu_online_mask;
-}
-
 static inline void setup_node_to_cpumask_map(void) { }
 
 #endif
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 5e06259e90e..632fb44b4cb 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -33,7 +33,7 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
  * The caller should also make sure he pins the user space address
- * so that the we don't result in page fault and sleep.
+ * so that we don't result in page fault and sleep.
  *
  * Here we special-case 1, 2 and 4-byte copy_*_user invocations.  On a fault
  * we return the initial request size (1, 2 or 4), as copy_*_user should do.
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index 8deaada61bc..6fb3c209a7e 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -341,7 +341,7 @@
 #define __NR_preadv		333
 #define __NR_pwritev		334
 #define __NR_rt_tgsigqueueinfo	335
-#define __NR_perf_counter_open	336
+#define __NR_perf_event_open	336
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index b9f3c60de5f..8d3ad0adbc6 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -659,8 +659,8 @@ __SYSCALL(__NR_preadv, sys_preadv)
 __SYSCALL(__NR_pwritev, sys_pwritev)
 #define __NR_rt_tgsigqueueinfo			297
 __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
-#define __NR_perf_counter_open			298
-__SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
+#define __NR_perf_event_open			298
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 77a68505419..d1414af9855 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -15,9 +15,12 @@
 #include <linux/numa.h>
 #include <linux/percpu.h>
 #include <linux/timer.h>
+#include <linux/io.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
 #include <asm/uv/uv_mmrs.h>
+#include <asm/irq_vectors.h>
+#include <asm/io_apic.h>
 
 
 /*
@@ -113,7 +116,7 @@
 /*
  * The largest possible NASID of a C or M brick (+ 2)
  */
-#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
+#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_BLADES * 2)
 
 struct uv_scir_s {
 	struct timer_list timer;
@@ -229,6 +232,20 @@ static inline unsigned long uv_gpa(void *v)
 	return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
+/* gnode -> pnode */
+static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
+{
+	return gpa >> uv_hub_info->m_val;
+}
+
+/* gpa -> pnode */
+static inline int uv_gpa_to_pnode(unsigned long gpa)
+{
+	unsigned long n_mask = (1UL << uv_hub_info->n_val) - 1;
+
+	return uv_gpa_to_gnode(gpa) & n_mask;
+}
+
 /* pnode, offset --> socket virtual */
 static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
 {
@@ -258,13 +275,13 @@ static inline unsigned long *uv_global_mmr32_address(int pnode,
 static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
 				 unsigned long val)
 {
-	*uv_global_mmr32_address(pnode, offset) = val;
+	writeq(val, uv_global_mmr32_address(pnode, offset));
 }
 
 static inline unsigned long uv_read_global_mmr32(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr32_address(pnode, offset);
+	return readq(uv_global_mmr32_address(pnode, offset));
 }
 
 /*
@@ -281,13 +298,13 @@ static inline unsigned long *uv_global_mmr64_address(int pnode,
 static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
 				unsigned long val)
 {
-	*uv_global_mmr64_address(pnode, offset) = val;
+	writeq(val, uv_global_mmr64_address(pnode, offset));
 }
 
 static inline unsigned long uv_read_global_mmr64(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr64_address(pnode, offset);
+	return readq(uv_global_mmr64_address(pnode, offset));
 }
 
 /*
@@ -301,22 +318,22 @@ static inline unsigned long *uv_local_mmr_address(unsigned long offset)
 
 static inline unsigned long uv_read_local_mmr(unsigned long offset)
 {
-	return *uv_local_mmr_address(offset);
+	return readq(uv_local_mmr_address(offset));
 }
 
 static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 {
-	*uv_local_mmr_address(offset) = val;
+	writeq(val, uv_local_mmr_address(offset));
 }
 
 static inline unsigned char uv_read_local_mmr8(unsigned long offset)
 {
-	return *((unsigned char *)uv_local_mmr_address(offset));
+	return readb(uv_local_mmr_address(offset));
 }
 
 static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
 {
-	*((unsigned char *)uv_local_mmr_address(offset)) = val;
+	writeb(val, uv_local_mmr_address(offset));
 }
 
 /*
@@ -420,9 +437,14 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 {
 	unsigned long val;
+	unsigned long dmode = dest_Fixed;
+
+	if (vector == NMI_VECTOR)
+		dmode = dest_NMI;
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
-			((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) |
+			((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
+			(dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
 			(vector << UVH_IPI_INT_VECTOR_SHFT);
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }