Merge branch 'next' into for-linus

28 files changed, 261 insertions, 361 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 60d2b2db0bc5..56f462cf22d2 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -142,6 +142,32 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 		return max_cstate;
 }
 
+static inline bool arch_has_acpi_pdc(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+	return (c->x86_vendor == X86_VENDOR_INTEL ||
+		c->x86_vendor == X86_VENDOR_CENTAUR);
+}
+
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	buf[2] |= ACPI_PDC_C_CAPABILITY_SMP;
+
+	if (cpu_has(c, X86_FEATURE_EST))
+		buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
+
+	if (cpu_has(c, X86_FEATURE_ACPI))
+		buf[2] |= ACPI_PDC_T_FFH;
+
+	/*
+	 * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
+	 */
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
+}
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0
diff --git a/arch/x86/include/asm/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/x86/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 613700f27a4a..637e1ec963c3 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
 #define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0f6c02f3b7d4..ac91eed21061 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -67,7 +67,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 	if (!dev->dma_mask)
 		return 0;
 
-	return addr + size <= *dev->dma_mask;
+	return addr + size - 1 <= *dev->dma_mask;
 }
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 8a024babe5e6..b4501ee223ad 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -239,7 +239,6 @@ extern int force_personality32;
 #endif /* !CONFIG_X86_32 */
 
 #define CORE_DUMP_USE_REGSET
-#define USE_ELF_CORE_DUMP
 #define ELF_EXEC_PAGESIZE	4096
 
 /* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
diff --git a/arch/x86/include/asm/geode.h b/arch/x86/include/asm/geode.h
index ad3c2ed75481..7cd73552a4e8 100644
--- a/arch/x86/include/asm/geode.h
+++ b/arch/x86/include/asm/geode.h
@@ -12,160 +12,7 @@
 
 #include <asm/processor.h>
 #include <linux/io.h>
-
-/* Generic southbridge functions */
-
-#define GEODE_DEV_PMS 0
-#define GEODE_DEV_ACPI 1
-#define GEODE_DEV_GPIO 2
-#define GEODE_DEV_MFGPT 3
-
-extern int geode_get_dev_base(unsigned int dev);
-
-/* Useful macros */
-#define geode_pms_base()	geode_get_dev_base(GEODE_DEV_PMS)
-#define geode_acpi_base()	geode_get_dev_base(GEODE_DEV_ACPI)
-#define geode_gpio_base()	geode_get_dev_base(GEODE_DEV_GPIO)
-#define geode_mfgpt_base()	geode_get_dev_base(GEODE_DEV_MFGPT)
-
-/* MSRS */
-
-#define MSR_GLIU_P2D_RO0	0x10000029
-
-#define MSR_LX_GLD_MSR_CONFIG	0x48002001
-#define MSR_LX_MSR_PADSEL	0x48002011	/* NOT 0x48000011; the data
-						 * sheet has the wrong value */
-#define MSR_GLCP_SYS_RSTPLL	0x4C000014
-#define MSR_GLCP_DOTPLL		0x4C000015
-
-#define MSR_LBAR_SMB		0x5140000B
-#define MSR_LBAR_GPIO		0x5140000C
-#define MSR_LBAR_MFGPT		0x5140000D
-#define MSR_LBAR_ACPI		0x5140000E
-#define MSR_LBAR_PMS		0x5140000F
-
-#define MSR_DIVIL_SOFT_RESET	0x51400017
-
-#define MSR_PIC_YSEL_LOW	0x51400020
-#define MSR_PIC_YSEL_HIGH	0x51400021
-#define MSR_PIC_ZSEL_LOW	0x51400022
-#define MSR_PIC_ZSEL_HIGH	0x51400023
-#define MSR_PIC_IRQM_LPC	0x51400025
-
-#define MSR_MFGPT_IRQ		0x51400028
-#define MSR_MFGPT_NR		0x51400029
-#define MSR_MFGPT_SETUP		0x5140002B
-
-#define MSR_LX_SPARE_MSR	0x80000011	/* DC-specific */
-
-#define MSR_GX_GLD_MSR_CONFIG	0xC0002001
-#define MSR_GX_MSR_PADSEL	0xC0002011
-
-/* Resource Sizes */
-
-#define LBAR_GPIO_SIZE		0xFF
-#define LBAR_MFGPT_SIZE		0x40
-#define LBAR_ACPI_SIZE		0x40
-#define LBAR_PMS_SIZE		0x80
-
-/* ACPI registers (PMS block) */
-
-/*
- * PM1_EN is only valid when VSA is enabled for 16 bit reads.
- * When VSA is not enabled, *always* read both PM1_STS and PM1_EN
- * with a 32 bit read at offset 0x0
- */
-
-#define PM1_STS			0x00
-#define PM1_EN			0x02
-#define PM1_CNT			0x08
-#define PM2_CNT			0x0C
-#define PM_TMR			0x10
-#define PM_GPE0_STS		0x18
-#define PM_GPE0_EN		0x1C
-
-/* PMC registers (PMS block) */
-
-#define PM_SSD			0x00
-#define PM_SCXA			0x04
-#define PM_SCYA			0x08
-#define PM_OUT_SLPCTL		0x0C
-#define PM_SCLK			0x10
-#define PM_SED			0x1
-#define PM_SCXD			0x18
-#define PM_SCYD			0x1C
-#define PM_IN_SLPCTL		0x20
-#define PM_WKD			0x30
-#define PM_WKXD			0x34
-#define PM_RD			0x38
-#define PM_WKXA			0x3C
-#define PM_FSD			0x40
-#define PM_TSD			0x44
-#define PM_PSD			0x48
-#define PM_NWKD			0x4C
-#define PM_AWKD			0x50
-#define PM_SSC			0x54
-
-/* VSA2 magic values */
-
-#define VSA_VRC_INDEX		0xAC1C
-#define VSA_VRC_DATA		0xAC1E
-#define VSA_VR_UNLOCK		0xFC53	/* unlock virtual register */
-#define VSA_VR_SIGNATURE	0x0003
-#define VSA_VR_MEM_SIZE		0x0200
-#define AMD_VSA_SIG		0x4132	/* signature is ascii 'VSA2' */
-#define GSW_VSA_SIG		0x534d  /* General Software signature */
-/* GPIO */
-
-#define GPIO_OUTPUT_VAL		0x00
-#define GPIO_OUTPUT_ENABLE	0x04
-#define GPIO_OUTPUT_OPEN_DRAIN	0x08
-#define GPIO_OUTPUT_INVERT	0x0C
-#define GPIO_OUTPUT_AUX1	0x10
-#define GPIO_OUTPUT_AUX2	0x14
-#define GPIO_PULL_UP		0x18
-#define GPIO_PULL_DOWN		0x1C
-#define GPIO_INPUT_ENABLE	0x20
-#define GPIO_INPUT_INVERT	0x24
-#define GPIO_INPUT_FILTER	0x28
-#define GPIO_INPUT_EVENT_COUNT	0x2C
-#define GPIO_READ_BACK		0x30
-#define GPIO_INPUT_AUX1		0x34
-#define GPIO_EVENTS_ENABLE	0x38
-#define GPIO_LOCK_ENABLE	0x3C
-#define GPIO_POSITIVE_EDGE_EN	0x40
-#define GPIO_NEGATIVE_EDGE_EN	0x44
-#define GPIO_POSITIVE_EDGE_STS	0x48
-#define GPIO_NEGATIVE_EDGE_STS	0x4C
-
-#define GPIO_MAP_X		0xE0
-#define GPIO_MAP_Y		0xE4
-#define GPIO_MAP_Z		0xE8
-#define GPIO_MAP_W		0xEC
-
-static inline u32 geode_gpio(unsigned int nr)
-{
-	BUG_ON(nr > 28);
-	return 1 << nr;
-}
-
-extern void geode_gpio_set(u32, unsigned int);
-extern void geode_gpio_clear(u32, unsigned int);
-extern int geode_gpio_isset(u32, unsigned int);
-extern void geode_gpio_setup_event(unsigned int, int, int);
-extern void geode_gpio_set_irq(unsigned int, unsigned int);
-
-static inline void geode_gpio_event_irq(unsigned int gpio, int pair)
-{
-	geode_gpio_setup_event(gpio, pair, 0);
-}
-
-static inline void geode_gpio_event_pme(unsigned int gpio, int pair)
-{
-	geode_gpio_setup_event(gpio, pair, 1);
-}
-
-/* Specific geode tests */
+#include <linux/cs5535.h>
 
 static inline int is_geode_gx(void)
 {
@@ -186,68 +33,4 @@ static inline int is_geode(void)
 	return (is_geode_gx() || is_geode_lx());
 }
 
-#ifdef CONFIG_MGEODE_LX
-extern int geode_has_vsa2(void);
-#else
-static inline int geode_has_vsa2(void)
-{
-	return 0;
-}
-#endif
-
-/* MFGPTs */
-
-#define MFGPT_MAX_TIMERS	8
-#define MFGPT_TIMER_ANY		(-1)
-
-#define MFGPT_DOMAIN_WORKING	1
-#define MFGPT_DOMAIN_STANDBY	2
-#define MFGPT_DOMAIN_ANY	(MFGPT_DOMAIN_WORKING | MFGPT_DOMAIN_STANDBY)
-
-#define MFGPT_CMP1		0
-#define MFGPT_CMP2		1
-
-#define MFGPT_EVENT_IRQ		0
-#define MFGPT_EVENT_NMI		1
-#define MFGPT_EVENT_RESET	3
-
-#define MFGPT_REG_CMP1		0
-#define MFGPT_REG_CMP2		2
-#define MFGPT_REG_COUNTER	4
-#define MFGPT_REG_SETUP		6
-
-#define MFGPT_SETUP_CNTEN	(1 << 15)
-#define MFGPT_SETUP_CMP2	(1 << 14)
-#define MFGPT_SETUP_CMP1	(1 << 13)
-#define MFGPT_SETUP_SETUP	(1 << 12)
-#define MFGPT_SETUP_STOPEN	(1 << 11)
-#define MFGPT_SETUP_EXTEN	(1 << 10)
-#define MFGPT_SETUP_REVEN	(1 << 5)
-#define MFGPT_SETUP_CLKSEL	(1 << 4)
-
-static inline void geode_mfgpt_write(int timer, u16 reg, u16 value)
-{
-	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-	outw(value, base + reg + (timer * 8));
-}
-
-static inline u16 geode_mfgpt_read(int timer, u16 reg)
-{
-	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-	return inw(base + reg + (timer * 8));
-}
-
-extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
-extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
-extern int geode_mfgpt_alloc_timer(int timer, int domain);
-
-#define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
-#define geode_mfgpt_release_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 0)
-
-#ifdef CONFIG_GEODE_MFGPT_TIMER
-extern int __init mfgpt_timer_setup(void);
-#else
-static inline int mfgpt_timer_setup(void) { return 0; }
-#endif
-
 #endif /* _ASM_X86_GEODE_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 08c48a81841f..eeac829a0f44 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -103,7 +103,8 @@ extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
 struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *);
+extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
+				      unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 950df434763f..f46b79f6c16c 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -254,6 +254,10 @@ struct kvm_reinject_control {
 	__u8 reserved[31];
 };
 
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 858baa061cfc..6c3fdd631ed3 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -108,10 +108,11 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
-extern struct atomic_notifier_head x86_mce_decoder_chain;
 
 #ifdef __KERNEL__
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <asm/atomic.h>
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b2ad75..1cd58cdbc03f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -12,6 +12,7 @@
 #define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
 #define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
 #define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
 
 /* EFER bits: */
 #define _EFER_SCE		0  /* SYSCALL/SYSRET */
@@ -123,6 +124,7 @@
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 2d228fc9b4b7..c5bc4c2d33f5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -27,6 +27,18 @@ struct msr {
 	};
 };
 
+struct msr_info {
+	u32 msr_no;
+	struct msr reg;
+	struct msr *msrs;
+	int err;
+};
+
+struct msr_regs_info {
+	u32 *regs;
+	int err;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
@@ -240,9 +252,9 @@ do {                                                            \
 #define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
 					     (u32)((val) >> 32))
 
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
 
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index 834a30295fab..3a57385d9fa7 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -120,7 +120,7 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 
 /* GPIO assignments */
 
-#define OLPC_GPIO_MIC_AC	geode_gpio(1)
+#define OLPC_GPIO_MIC_AC	1
 #define OLPC_GPIO_DCON_IRQ	geode_gpio(7)
 #define OLPC_GPIO_THRM_ALRM	geode_gpio(10)
 #define OLPC_GPIO_SMB_CLK	geode_gpio(14)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index efb38994859c..dd59a85a918f 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -731,34 +731,34 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
-static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+static inline int arch_spin_is_locked(struct arch_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
 }
 
-static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+static inline int arch_spin_is_contended(struct arch_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
 }
-#define __raw_spin_is_contended	__raw_spin_is_contended
+#define arch_spin_is_contended	arch_spin_is_contended
 
-static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
 {
 	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
 }
 
-static __always_inline void __raw_spin_lock_flags(struct raw_spinlock *lock,
+static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
 						  unsigned long flags)
 {
 	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
 }
 
-static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
+static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
 }
 
-static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
 {
 	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
 }
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 9357473c8da0..b1e70d51e40c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -318,14 +318,14 @@ struct pv_mmu_ops {
 			   phys_addr_t phys, pgprot_t flags);
 };
 
-struct raw_spinlock;
+struct arch_spinlock;
 struct pv_lock_ops {
-	int (*spin_is_locked)(struct raw_spinlock *lock);
-	int (*spin_is_contended)(struct raw_spinlock *lock);
-	void (*spin_lock)(struct raw_spinlock *lock);
-	void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
-	int (*spin_trylock)(struct raw_spinlock *lock);
-	void (*spin_unlock)(struct raw_spinlock *lock);
+	int (*spin_is_locked)(struct arch_spinlock *lock);
+	int (*spin_is_contended)(struct arch_spinlock *lock);
+	void (*spin_lock)(struct arch_spinlock *lock);
+	void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags);
+	int (*spin_trylock)(struct arch_spinlock *lock);
+	void (*spin_unlock)(struct arch_spinlock *lock);
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8d9f8548a870..1380367dabd9 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -19,6 +19,7 @@
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
 #define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
 #define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
 #define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
 #define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6f8ec1c37e0a..fc801bab1b3b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,7 +181,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 				unsigned int *ecx, unsigned int *edx)
 {
 	/* ecx is often an input as well as an output. */
-	asm("cpuid"
+	asm volatile("cpuid"
 	    : "=a" (*eax),
 	      "=b" (*ebx),
 	      "=c" (*ecx),
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 3d11fd0f44c5..9d369f680321 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -292,6 +292,8 @@ extern void user_enable_block_step(struct task_struct *);
 #define arch_has_block_step()	(boot_cpu_data.x86 >= 6)
 #endif
 
+#define ARCH_HAS_USER_SINGLE_STEP_INFO
+
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 4e77853321db..3089f70c0c52 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -58,7 +58,7 @@
 #if (NR_CPUS < 256)
 #define TICKET_SHIFT 8
 
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
 	short inc = 0x0100;
 
@@ -77,7 +77,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 		: "memory", "cc");
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
 	int tmp, new;
 
@@ -96,7 +96,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 	return tmp;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
 		     : "+m" (lock->slock)
@@ -106,7 +106,7 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 #else
 #define TICKET_SHIFT 16
 
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
 	int inc = 0x00010000;
 	int tmp;
@@ -127,7 +127,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 		     : "memory", "cc");
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
 	int tmp;
 	int new;
@@ -149,7 +149,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 	return tmp;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
 		     : "+m" (lock->slock)
@@ -158,14 +158,14 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 }
 #endif
 
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
 	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
 }
 
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
@@ -174,43 +174,43 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 
 #ifndef CONFIG_PARAVIRT_SPINLOCKS
 
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
 	return __ticket_spin_is_locked(lock);
 }
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
 	return __ticket_spin_is_contended(lock);
 }
-#define __raw_spin_is_contended	__raw_spin_is_contended
+#define arch_spin_is_contended	arch_spin_is_contended
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	__ticket_spin_lock(lock);
 }
 
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	return __ticket_spin_trylock(lock);
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	__ticket_spin_unlock(lock);
 }
 
-static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 						  unsigned long flags)
 {
-	__raw_spin_lock(lock);
+	arch_spin_lock(lock);
 }
 
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
 
-static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-	while (__raw_spin_is_locked(lock))
+	while (arch_spin_is_locked(lock))
 		cpu_relax();
 }
 
@@ -232,7 +232,7 @@ static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-static inline int __raw_read_can_lock(raw_rwlock_t *lock)
+static inline int arch_read_can_lock(arch_rwlock_t *lock)
 {
 	return (int)(lock)->lock > 0;
 }
@@ -241,12 +241,12 @@ static inline int __raw_read_can_lock(raw_rwlock_t *lock)
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-static inline int __raw_write_can_lock(raw_rwlock_t *lock)
+static inline int arch_write_can_lock(arch_rwlock_t *lock)
 {
 	return (lock)->lock == RW_LOCK_BIAS;
 }
 
-static inline void __raw_read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
 		     "jns 1f\n"
@@ -255,7 +255,7 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 		     ::LOCK_PTR_REG (rw) : "memory");
 }
 
-static inline void __raw_write_lock(raw_rwlock_t *rw)
+static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t"
 		     "jz 1f\n"
@@ -264,7 +264,7 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 		     ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory");
 }
 
-static inline int __raw_read_trylock(raw_rwlock_t *lock)
+static inline int arch_read_trylock(arch_rwlock_t *lock)
 {
 	atomic_t *count = (atomic_t *)lock;
 
@@ -274,7 +274,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
 	return 0;
 }
 
-static inline int __raw_write_trylock(raw_rwlock_t *lock)
+static inline int arch_write_trylock(arch_rwlock_t *lock)
 {
 	atomic_t *count = (atomic_t *)lock;
 
@@ -284,23 +284,23 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock)
 	return 0;
 }
 
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
 }
 
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
+static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
 	asm volatile(LOCK_PREFIX "addl %1, %0"
 		     : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
 }
 
-#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
-#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define _raw_spin_relax(lock)	cpu_relax()
-#define _raw_read_relax(lock)	cpu_relax()
-#define _raw_write_relax(lock)	cpu_relax()
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
 
 /* The {read|write|spin}_lock() on x86 are full memory barriers. */
 static inline void smp_mb__after_lock(void) { }
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 845f81c87091..dcb48b2edc11 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -5,16 +5,16 @@
 # error "please don't include this file directly"
 #endif
 
-typedef struct raw_spinlock {
+typedef struct arch_spinlock {
 	unsigned int slock;
-} raw_spinlock_t;
+} arch_spinlock_t;
 
-#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
 
 typedef struct {
 	unsigned int lock;
-} raw_rwlock_t;
+} arch_rwlock_t;
 
-#define __RAW_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
+#define __ARCH_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
 
 #endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index cf86a5e73815..35e89122a42f 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -5,6 +5,29 @@ extern int kstack_depth_to_print;
 
 int x86_is_stack_id(int id, char *name);
 
+struct thread_info;
+struct stacktrace_ops;
+
+typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+				      unsigned long *stack,
+				      unsigned long bp,
+				      const struct stacktrace_ops *ops,
+				      void *data,
+				      unsigned long *end,
+				      int *graph);
+
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+		    unsigned long *stack, unsigned long bp,
+		    const struct stacktrace_ops *ops, void *data,
+		    unsigned long *end, int *graph);
+
+extern unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+		       unsigned long *stack, unsigned long bp,
+		       const struct stacktrace_ops *ops, void *data,
+		       unsigned long *end, int *graph);
+
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
@@ -14,6 +37,7 @@ struct stacktrace_ops {
 	void (*address)(void *data, unsigned long address, int reliable);
 	/* On negative return stop dumping */
 	int (*stack)(void *data, char *name);
+	walk_stack_t	walk_stack;
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 87ffcb12a1b8..8085277e1b8b 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -5,13 +5,17 @@
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern int pci_swiotlb_init(void);
+extern int __init pci_swiotlb_detect(void);
+extern void __init pci_swiotlb_init(void);
 #else
 #define swiotlb 0
-static inline int pci_swiotlb_init(void)
+static inline int pci_swiotlb_detect(void)
 {
 	return 0;
 }
+static inline void pci_swiotlb_init(void)
+{
+}
 #endif
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 4a5a089e1c62..d5f69045c100 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -30,7 +30,6 @@ struct mmap_arg_struct;
 asmlinkage long sys32_mmap(struct mmap_arg_struct __user *);
 asmlinkage long sys32_mprotect(unsigned long, size_t, unsigned long);
 
-asmlinkage long sys32_pipe(int __user *);
 struct sigaction32;
 struct old_sigaction32;
 asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *,
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 1bb6e395881c..8868b9420b0e 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -18,16 +18,24 @@
 /* Common in X86_32 and X86_64 */
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+long sys_iopl(unsigned int, struct pt_regs *);
 
 /* kernel/process.c */
 int sys_fork(struct pt_regs *);
 int sys_vfork(struct pt_regs *);
+long sys_execve(char __user *, char __user * __user *,
+		char __user * __user *, struct pt_regs *);
+long sys_clone(unsigned long, unsigned long, void __user *,
+	       void __user *, struct pt_regs *);
 
 /* kernel/ldt.c */
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 long sys_rt_sigreturn(struct pt_regs *);
+long sys_sigaltstack(const stack_t __user *, stack_t __user *,
+		     struct pt_regs *);
+
 
 /* kernel/tls.c */
 asmlinkage int sys_set_thread_area(struct user_desc __user *);
@@ -35,18 +43,11 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *);
 
 /* X86_32 only */
 #ifdef CONFIG_X86_32
-/* kernel/ioport.c */
-long sys_iopl(struct pt_regs *);
-
-/* kernel/process_32.c */
-int sys_clone(struct pt_regs *);
-int sys_execve(struct pt_regs *);
 
 /* kernel/signal.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
 			     struct old_sigaction __user *);
-int sys_sigaltstack(struct pt_regs *);
 unsigned long sys_sigreturn(struct pt_regs *);
 
 /* kernel/sys_i386_32.c */
@@ -62,28 +63,15 @@ asmlinkage int sys_uname(struct old_utsname __user *);
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
 /* kernel/vm86_32.c */
-int sys_vm86old(struct pt_regs *);
-int sys_vm86(struct pt_regs *);
+int sys_vm86old(struct vm86_struct __user *, struct pt_regs *);
+int sys_vm86(unsigned long, unsigned long, struct pt_regs *);
 
 #else /* CONFIG_X86_32 */
 
 /* X86_64 only */
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
 /* kernel/process_64.c */
-asmlinkage long sys_clone(unsigned long, unsigned long,
-			  void __user *, void __user *,
-			  struct pt_regs *);
-asmlinkage long sys_execve(char __user *, char __user * __user *,
-			   char __user * __user *,
-			   struct pt_regs *);
 long sys_arch_prctl(int, unsigned long);
 
-/* kernel/signal.c */
-asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
-				struct pt_regs *);
-
 /* kernel/sys_x86_64.c */
 struct new_utsname;
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 40e37b10c6c0..c5087d796587 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -35,11 +35,16 @@
 # endif
 #endif
 
-/* Node not present */
-#define NUMA_NO_NODE	(-1)
+/*
+ * to preserve the visibility of NUMA_NO_NODE definition,
+ * moved to there from here.  May be used independent of
+ * CONFIG_NUMA.
+ */
+#include <linux/numa.h>
 
 #ifdef CONFIG_NUMA
 #include <linux/cpumask.h>
+
 #include <asm/mpspec.h>
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 0c9825e97f36..088d09fb1615 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -205,14 +205,13 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 	else
 		copy_from_user_overflow();
 
-	return ret;
+	return n;
 }
 
 long __must_check strncpy_from_user(char *dst, const char __user *src,
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 46324c6a4f6e..535e421498f6 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -30,16 +30,15 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	might_fault();
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 #ifdef CONFIG_DEBUG_VM
 	else
 		WARN(1, "Buffer overflow detected!\n");
 #endif
-	return ret;
+	return n;
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 7ed17ff502b9..2751f3075d8b 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -76,15 +76,6 @@ union partition_info_u {
 	};
 };
 
-union uv_watchlist_u {
-	u64	val;
-	struct {
-		u64	blade	: 16,
-			size	: 32,
-			filler	: 16;
-	};
-};
-
 enum uv_memprotect {
 	UV_MEMPROT_RESTRICT_ACCESS,
 	UV_MEMPROT_ALLOW_AMO,
@@ -100,7 +91,7 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
-extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int,
+extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int,
 					unsigned long *);
 extern int uv_bios_mq_watchlist_free(int, int);
 extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index d1414af98559..40be813fefb1 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -31,20 +31,20 @@
  *		  contiguous (although various IO spaces may punch holes in
  *		  it)..
  *
- * 	N	- Number of bits in the node portion of a socket physical
- * 		  address.
+ *	N	- Number of bits in the node portion of a socket physical
+ *		  address.
  *
- * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
- * 	 	  routers always have low bit of 1, C/MBricks have low bit
- * 		  equal to 0. Most addressing macros that target UV hub chips
- * 		  right shift the NASID by 1 to exclude the always-zero bit.
- * 		  NASIDs contain up to 15 bits.
+ *	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ *		  routers always have low bit of 1, C/MBricks have low bit
+ *		  equal to 0. Most addressing macros that target UV hub chips
+ *		  right shift the NASID by 1 to exclude the always-zero bit.
+ *		  NASIDs contain up to 15 bits.
  *
  *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
  *		  of nasids.
  *
- * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
- * 		  of the nasid for socket usage.
+ *	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ *		  of the nasid for socket usage.
  *
  *
  *  NumaLink Global Physical Address Format:
@@ -71,12 +71,12 @@
  *
  *
  * APICID format
- * 	NOTE!!!!!! This is the current format of the APICID. However, code
- * 	should assume that this will change in the future. Use functions
- * 	in this file for all APICID bit manipulations and conversion.
+ *	NOTE!!!!!! This is the current format of the APICID. However, code
+ *	should assume that this will change in the future. Use functions
+ *	in this file for all APICID bit manipulations and conversion.
  *
- * 		1111110000000000
- * 		5432109876543210
+ *		1111110000000000
+ *		5432109876543210
  *		pppppppppplc0cch
  *		sssssssssss
  *
@@ -89,9 +89,9 @@
  *	Note: Processor only supports 12 bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
  *
- * 	      Unless otherwise specified, all references to APICID refer to
- * 	      the FULL value contained in ACPI tables, not the subset in the
- * 	      processor APICID register.
+ *	      Unless otherwise specified, all references to APICID refer to
+ *	      the FULL value contained in ACPI tables, not the subset in the
+ *	      processor APICID register.
  */
 
 
@@ -151,16 +151,16 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
  * Local & Global MMR space macros.
- * 	Note: macros are intended to be used ONLY by inline functions
- * 	in this file - not by other kernel code.
- * 		n -  NASID (full 15-bit global nasid)
- * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
- * 		p -  PNODE (local part of nsids, right shifted 1)
+ *	Note: macros are intended to be used ONLY by inline functions
+ *	in this file - not by other kernel code.
+ *		n -  NASID (full 15-bit global nasid)
+ *		g -  GNODE (full 15-bit global nasid, right shifted 1)
+ *		p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
 #define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
@@ -172,6 +172,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
 #define UV_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
 
+#define UV_GLOBAL_GRU_MMR_BASE		0x4000000
+
 #define UV_GLOBAL_MMR32_PNODE_SHIFT	15
 #define UV_GLOBAL_MMR64_PNODE_SHIFT	26
 
@@ -213,8 +215,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
- * 	Note: use the standard __pa() & __va() macros for converting
- * 	      between socket virtual and socket physical addresses.
+ *	Note: use the standard __pa() & __va() macros for converting
+ *	      between socket virtual and socket physical addresses.
  */
 
 /* socket phys RAM --> UV global physical address */
@@ -232,6 +234,26 @@ static inline unsigned long uv_gpa(void *v)
 	return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
+/* Top two bits indicate the requested address is in MMR space.  */
+static inline int
+uv_gpa_in_mmr_space(unsigned long gpa)
+{
+	return (gpa >> 62) == 0x3UL;
+}
+
+/* UV global physical address --> socket phys RAM */
+static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
+{
+	unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
+	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
+
+	if (paddr >= remap_base && paddr < remap_base + remap_top)
+		paddr -= remap_base;
+	return paddr;
+}
+
+
 /* gnode -> pnode */
 static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
 {
@@ -265,21 +287,18 @@ static inline int uv_apicid_to_pnode(int apicid)
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR32_BASE |
 		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
-				 unsigned long val)
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr32_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr32(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr32_address(pnode, offset));
 }
@@ -288,26 +307,42 @@ static inline unsigned long uv_read_global_mmr32(int pnode,
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR64_BASE |
 		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
-				unsigned long val)
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr64_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr64(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr64_address(pnode, offset));
 }
 
 /*
+ * Global MMR space addresses when referenced by the GRU. (GRU does
+ * NOT use socket addressing).
+ */
+static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long offset)
+{
+	return UV_GLOBAL_GRU_MMR_BASE | offset | (pnode << uv_hub_info->m_val);
+}
+
+static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
+{
+	writeb(val, uv_global_mmr64_address(pnode, offset));
+}
+
+static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset)
+{
+	return readb(uv_global_mmr64_address(pnode, offset));
+}
+
+/*
  * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
@@ -426,14 +461,28 @@ static inline void uv_set_scir_bits(unsigned char value)
 	}
 }
 
+static inline unsigned long uv_scir_offset(int apicid)
+{
+	return SCIR_LOCAL_MMR_BASE | (apicid & 0x3f);
+}
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
 	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+		uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
+				uv_cpu_hub_info(cpu)->scir.offset, value);
 		uv_cpu_hub_info(cpu)->scir.state = value;
-		uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
 	}
 }
 
+static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
+{
+	return (1UL << UVH_IPI_INT_SEND_SHFT) |
+			((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
+			(mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
+			(vector << UVH_IPI_INT_VECTOR_SHFT);
+}
+
 static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 {
 	unsigned long val;
@@ -442,12 +491,21 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 	if (vector == NMI_VECTOR)
 		dmode = dest_NMI;
 
-	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
-			((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
-			(dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
-			(vector << UVH_IPI_INT_VECTOR_SHFT);
+	val = uv_hub_ipi_value(apicid, vector, dmode);
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
 
+/*
+ * Get the minimum revision number of the hub chips within the partition.
+ *     1 - initial rev 1.0 silicon
+ *     2 - rev 2.0 production silicon
+ */
+static inline int uv_get_min_hub_revision_id(void)
+{
+	extern int uv_min_hub_revision_id;
+
+	return uv_min_hub_revision_id;
+}
+
 #endif /* CONFIG_X86_64 */
 #endif /* _ASM_X86_UV_UV_HUB_H */