Merge branch 'iommu/fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu into x86/urgent

18 files changed, 213 insertions, 335 deletions

diff --git a/arch/x86/include/asm/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h
new file mode 100644
index 00000000000..d370ee36a18
--- /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/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0f6c02f3b7d..ac91eed2106 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 8a024babe5e..b4501ee223a 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 ad3c2ed7548..7cd73552a4e 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/olpc.h b/arch/x86/include/asm/olpc.h
index 834a30295fa..3a57385d9fa 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 efb38994859..dd59a85a918 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 9357473c8da..b1e70d51e40 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/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index b399988eee3..b4bf9a942ed 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -118,11 +118,27 @@ extern int __init pcibios_init(void);
 
 /* pci-mmconfig.c */
 
+/* "PCI MMCONFIG %04x [bus %02x-%02x]" */
+#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2)
+
+struct pci_mmcfg_region {
+	struct list_head list;
+	struct resource res;
+	u64 address;
+	char __iomem *virt;
+	u16 segment;
+	u8 start_bus;
+	u8 end_bus;
+	char name[PCI_MMCFG_RESOURCE_NAME_LEN];
+};
+
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
+extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
+
+extern struct list_head pci_mmcfg_list;
 
-extern struct acpi_mcfg_allocation *pci_mmcfg_config;
-extern int pci_mmcfg_config_num;
+#define PCI_MMCFG_BUS_OFFSET(bus)      ((bus) << 20)
 
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b65a36defeb..0c44196b78a 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -74,31 +74,31 @@ extern void __bad_percpu_size(void);
 
 #define percpu_to_op(op, var, val)			\
 do {							\
-	typedef typeof(var) T__;			\
+	typedef typeof(var) pto_T__;			\
 	if (0) {					\
-		T__ tmp__;				\
-		tmp__ = (val);				\
+		pto_T__ pto_tmp__;			\
+		pto_tmp__ = (val);			\
 	}						\
 	switch (sizeof(var)) {				\
 	case 1:						\
 		asm(op "b %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "qi" ((T__)(val)));		\
+		    : "qi" ((pto_T__)(val)));		\
 		break;					\
 	case 2:						\
 		asm(op "w %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
+		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 4:						\
 		asm(op "l %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
+		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 8:						\
 		asm(op "q %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "re" ((T__)(val)));		\
+		    : "re" ((pto_T__)(val)));		\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
@@ -106,31 +106,31 @@ do {							\
 
 #define percpu_from_op(op, var, constraint)		\
 ({							\
-	typeof(var) ret__;				\
+	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
 		asm(op "b "__percpu_arg(1)",%0"		\
-		    : "=q" (ret__)			\
+		    : "=q" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 2:						\
 		asm(op "w "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 4:						\
 		asm(op "l "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 8:						\
 		asm(op "q "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
-	ret__;						\
+	pfo_ret__;					\
 })
 
 /*
@@ -153,6 +153,84 @@ do {							\
 #define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
 #define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
 
+#define __this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+
+#define __this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+/*
+ * Per cpu atomic 64 bit operations are only available under 64 bit.
+ * 32 bit must fall back to generic operations.
+ */
+#ifdef CONFIG_X86_64
+#define __this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#endif
+
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 3d11fd0f44c..9d369f68032 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 4e77853321d..3089f70c0c5 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 845f81c8709..dcb48b2edc1 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/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 9af9decb38c..d5f69045c10 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 *,
@@ -57,9 +56,6 @@ asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32);
 asmlinkage long sys32_personality(unsigned long);
 asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
 
-asmlinkage long sys32_mmap2(unsigned long, unsigned long, unsigned long,
-			    unsigned long, unsigned long, unsigned long);
-
 struct oldold_utsname;
 struct old_utsname;
 asmlinkage long sys32_olduname(struct oldold_utsname __user *);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index b0ce7806170..8868b9420b0 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -56,8 +56,6 @@ struct sel_arg_struct;
 struct oldold_utsname;
 struct old_utsname;
 
-asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
-			  unsigned long, unsigned long, unsigned long);
 asmlinkage int old_mmap(struct mmap_arg_struct __user *);
 asmlinkage int old_select(struct sel_arg_struct __user *);
 asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 40e37b10c6c..c5087d79658 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/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 7ed17ff502b..2751f3075d8 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 d1414af9855..811bfabc80b 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -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
 
@@ -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)
 {
@@ -308,6 +330,15 @@ static inline unsigned long uv_read_global_mmr64(int pnode,
 }
 
 /*
+ * 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);
+}
+
+/*
  * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
@@ -434,6 +465,14 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char 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;
@@ -442,10 +481,7 @@ 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);
 }
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d5b7e90c0ed..396ff4cc8ed 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,31 +37,4 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-enum xen_domain_type {
-	XEN_NATIVE,		/* running on bare hardware    */
-	XEN_PV_DOMAIN,		/* running in a PV domain      */
-	XEN_HVM_DOMAIN,		/* running in a Xen hvm domain */
-};
-
-#ifdef CONFIG_XEN
-extern enum xen_domain_type xen_domain_type;
-#else
-#define xen_domain_type		XEN_NATIVE
-#endif
-
-#define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain() &&			\
-				 xen_domain_type == XEN_PV_DOMAIN)
-#define xen_hvm_domain()	(xen_domain() &&			\
-				 xen_domain_type == XEN_HVM_DOMAIN)
-
-#ifdef CONFIG_XEN_DOM0
-#include <xen/interface/xen.h>
-
-#define xen_initial_domain()	(xen_pv_domain() && \
-				 xen_start_info->flags & SIF_INITDOMAIN)
-#else  /* !CONFIG_XEN_DOM0 */
-#define xen_initial_domain()	(0)
-#endif	/* CONFIG_XEN_DOM0 */
-
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */