Merge branch 'linus' into idle-test

36 files changed, 494 insertions, 146 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 55d106b..211ca3f 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -185,17 +185,16 @@ struct bootnode;
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
-extern int acpi_get_nodes(struct bootnode *physnodes);
+extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+				unsigned long end);
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
 #define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
+#ifdef CONFIG_NUMA_EMU
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
 				   int num_nodes);
-#else
-static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
-				   int num_nodes)
-{
-}
 #endif
+#endif /* CONFIG_ACPI_NUMA */
 
 #define acpi_unlazy_tlb(x)	leave_mm(x)
 
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 76561d2..13009d1 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -66,6 +66,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
 extern void alternatives_smp_module_del(struct module *mod);
 extern void alternatives_smp_switch(int smp);
 extern int alternatives_text_reserved(void *start, void *end);
+extern bool skip_smp_alternatives;
 #else
 static inline void alternatives_smp_module_add(struct module *mod, char *name,
 					       void *locks, void *locks_end,
@@ -180,8 +181,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
+struct text_poke_param {
+	void *addr;
+	const void *opcode;
+	size_t len;
+};
+
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
+extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 #define IDEAL_NOP_SIZE_5 5
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index c8517f8..64dc82e 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -3,36 +3,64 @@
 
 #include <linux/pci.h>
 
-extern struct pci_device_id k8_nb_ids[];
+struct amd_nb_bus_dev_range {
+	u8 bus;
+	u8 dev_base;
+	u8 dev_limit;
+};
+
+extern struct pci_device_id amd_nb_misc_ids[];
+extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
 struct bootnode;
 
-extern int early_is_k8_nb(u32 value);
-extern int cache_k8_northbridges(void);
-extern void k8_flush_garts(void);
-extern int k8_get_nodes(struct bootnode *nodes);
-extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
-extern int k8_scan_nodes(void);
+extern int early_is_amd_nb(u32 value);
+extern int amd_cache_northbridges(void);
+extern void amd_flush_garts(void);
+extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
+extern int amd_scan_nodes(void);
+
+#ifdef CONFIG_NUMA_EMU
+extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes);
+extern void amd_get_nodes(struct bootnode *nodes);
+#endif
 
-struct k8_northbridge_info {
+struct amd_northbridge {
+	struct pci_dev *misc;
+};
+
+struct amd_northbridge_info {
 	u16 num;
-	u8 gart_supported;
-	struct pci_dev **nb_misc;
+	u64 flags;
+	struct amd_northbridge *nb;
 };
-extern struct k8_northbridge_info k8_northbridges;
+extern struct amd_northbridge_info amd_northbridges;
+
+#define AMD_NB_GART			0x1
+#define AMD_NB_L3_INDEX_DISABLE		0x2
 
 #ifdef CONFIG_AMD_NB
 
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline int amd_nb_num(void)
 {
-	return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
+	return amd_northbridges.num;
 }
 
-#else
+static inline int amd_nb_has_feature(int feature)
+{
+	return ((amd_northbridges.flags & feature) == feature);
+}
 
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline struct amd_northbridge *node_to_amd_nb(int node)
 {
-	return NULL;
+	return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
 }
+
+#else
+
+#define amd_nb_num(x)		0
+#define amd_nb_has_feature(x)	false
+#define node_to_amd_nb(x)	NULL
+
 #endif
 
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f6ce0bd..5e3969c3 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -234,16 +234,17 @@ extern void init_bsp_APIC(void);
 extern void setup_local_APIC(void);
 extern void end_local_APIC_setup(void);
 extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
 extern void setup_boot_APIC_clock(void);
 extern void setup_secondary_APIC_clock(void);
 extern int APIC_init_uniprocessor(void);
 extern void enable_NMI_through_LVT0(void);
+extern int apic_force_enable(void);
 
 /*
  * On 32bit this is mach-xxx local
  */
 #ifdef CONFIG_X86_64
-extern void early_init_lapic_mapping(void);
 extern int apic_is_clustered_box(void);
 #else
 static inline int apic_is_clustered_box(void)
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index a859ca4..47a30ff 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -145,6 +145,7 @@
 
 #ifdef CONFIG_X86_32
 # define MAX_IO_APICS 64
+# define MAX_LOCAL_APIC 256
 #else
 # define MAX_IO_APICS 128
 # define MAX_LOCAL_APIC 32768
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 8e62185..c8bfe63 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -124,6 +124,7 @@ enum {
 	X86_SUBARCH_LGUEST,
 	X86_SUBARCH_XEN,
 	X86_SUBARCH_MRST,
+	X86_SUBARCH_CE4100,
 	X86_NR_SUBARCHS,
 };
 
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b81002f..078ad0c 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -94,7 +94,7 @@ static inline void hw_breakpoint_disable(void)
 
 static inline int hw_breakpoint_active(void)
 {
-	return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
+	return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
 }
 
 extern void aout_dump_debugregs(struct user *dump);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 9479a03..4729b2b 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -116,7 +116,11 @@ enum fixed_addresses {
 #endif
 	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
 	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
+#ifdef	CONFIG_X86_MRST
+	FIX_LNW_VRTC,
+#endif
 	__end_of_permanent_fixed_addresses,
+
 	/*
 	 * 256 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
index 49dbfdf..91d915a 100644
--- a/arch/x86/include/asm/gpio.h
+++ b/arch/x86/include/asm/gpio.h
@@ -38,12 +38,9 @@ static inline int gpio_cansleep(unsigned int gpio)
 	return __gpio_cansleep(gpio);
 }
 
-/*
- * Not implemented, yet.
- */
 static inline int gpio_to_irq(unsigned int gpio)
 {
-	return -ENOSYS;
+	return __gpio_to_irq(gpio);
 }
 
 static inline int irq_to_gpio(unsigned int irq)
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index ff2546c..7a15153 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,6 +20,9 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
+#include <asm/kvm_para.h>
+#include <asm/xen/hypervisor.h>
+
 extern void init_hypervisor(struct cpuinfo_x86 *c);
 extern void init_hypervisor_platform(void);
 
@@ -47,4 +50,13 @@ extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 
+static inline bool hypervisor_x2apic_available(void)
+{
+	if (kvm_para_available())
+		return true;
+	if (xen_x2apic_para_available())
+		return true;
+	return false;
+}
+
 #endif
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 4aa2bb3..ef32890 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -93,6 +93,17 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 	int err;
 
 	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxrstorq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+		     : [fx] "m" (*fx), "0" (0));
+#else
 	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -102,6 +113,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
 		     : [fx] "R" (fx), "m" (*fx), "0" (0));
+#endif
 	return err;
 }
 
@@ -119,6 +131,17 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		return -EFAULT;
 
 	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxsaveq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), [fx] "=m" (*fx)
+		     : "0" (0));
+#else
 	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -128,6 +151,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
 		     : [fx] "R" (fx), "0" (0));
+#endif
 	if (unlikely(err) &&
 	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
 		err = -EFAULT;
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index a6b28d0..f327d38 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -159,7 +159,7 @@ struct io_apic_irq_attr;
 extern int io_apic_set_pci_routing(struct device *dev, int irq,
 		 struct io_apic_irq_attr *irq_attr);
 void setup_IO_APIC_irq_extra(u32 gsi);
-extern void ioapic_init_mappings(void);
+extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
@@ -168,10 +168,10 @@ extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
-extern void probe_nr_irqs_gsi(void);
 extern int get_nr_irqs_gsi(void);
 
 extern void setup_ioapic_ids_from_mpc(void);
+extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
 struct mp_ioapic_gsi{
 	u32 gsi_base;
@@ -184,14 +184,15 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi);
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
 extern void __init pre_init_apic_IRQ0(void);
 
+extern void mp_save_irq(struct mpc_intsrc *m);
+
 #else  /* !CONFIG_X86_IO_APIC */
 
 #define io_apic_assign_pci_irqs 0
 #define setup_ioapic_ids_from_mpc x86_init_noop
 static const int timer_through_8259 = 0;
-static inline void ioapic_init_mappings(void)	{ }
+static inline void ioapic_and_gsi_init(void) { }
 static inline void ioapic_insert_resources(void) { }
-static inline void probe_nr_irqs_gsi(void)	{ }
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
 
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 13b0eba..ba870bb 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG
-#endif
-
 #ifdef CONFIG_X86_32
 extern void irq_ctx_init(int cpu);
 #else
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 5bdfca8..ca242d3 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -18,7 +18,6 @@ enum die_val {
 	DIE_TRAP,
 	DIE_GPF,
 	DIE_CALL,
-	DIE_NMI_IPI,
 	DIE_PAGE_FAULT,
 	DIE_NMIUNKNOWN,
 };
@@ -28,7 +27,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_registers(struct pt_regs *regs);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-		       unsigned long *sp, unsigned long bp);
+		       unsigned long *sp);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern void show_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f792060..72a8b52 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -7,9 +7,19 @@
 
 #include <asm/mc146818rtc.h>
 
+#define NMI_REASON_PORT		0x61
+
+#define NMI_REASON_SERR		0x80
+#define NMI_REASON_IOCHK	0x40
+#define NMI_REASON_MASK		(NMI_REASON_SERR | NMI_REASON_IOCHK)
+
+#define NMI_REASON_CLEAR_SERR	0x04
+#define NMI_REASON_CLEAR_IOCHK	0x08
+#define NMI_REASON_CLEAR_MASK	0x0f
+
 static inline unsigned char get_nmi_reason(void)
 {
-	return inb(0x61);
+	return inb(NMI_REASON_PORT);
 }
 
 static inline void reassert_nmi(void)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c62c13c..eb16e94 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
 
+/* Interrupt Handler for core thermal thresholds */
+extern int (*platform_thermal_notify)(__u64 msr_val);
+
 #ifdef CONFIG_X86_THERMAL_VECTOR
 extern void mcheck_intel_therm_init(void);
 #else
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index ef51b50..2421507 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -48,6 +48,12 @@ static inline struct microcode_ops * __init init_intel_microcode(void)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern struct microcode_ops * __init init_amd_microcode(void);
+
+static inline void get_ucode_data(void *to, const u8 *from, size_t n)
+{
+	memcpy(to, from, n);
+}
+
 #else
 static inline struct microcode_ops * __init init_amd_microcode(void)
 {
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index c82868e..0c90dd9 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -5,8 +5,9 @@
 
 #include <asm/mpspec_def.h>
 #include <asm/x86_init.h>
+#include <asm/apicdef.h>
 
-extern int apic_version[MAX_APICS];
+extern int apic_version[];
 extern int pic_mode;
 
 #ifdef CONFIG_X86_32
@@ -107,7 +108,7 @@ extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
 				 int active_high_low);
 #endif /* CONFIG_ACPI */
 
-#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
+#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_LOCAL_APIC)
 
 struct physid_mask {
 	unsigned long mask[PHYSID_ARRAY_SIZE];
@@ -122,31 +123,31 @@ typedef struct physid_mask physid_mask_t;
 	test_and_set_bit(physid, (map).mask)
 
 #define physids_and(dst, src1, src2)					\
-	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
 
 #define physids_or(dst, src1, src2)					\
-	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
 
 #define physids_clear(map)					\
-	bitmap_zero((map).mask, MAX_APICS)
+	bitmap_zero((map).mask, MAX_LOCAL_APIC)
 
 #define physids_complement(dst, src)				\
-	bitmap_complement((dst).mask, (src).mask, MAX_APICS)
+	bitmap_complement((dst).mask, (src).mask, MAX_LOCAL_APIC)
 
 #define physids_empty(map)					\
-	bitmap_empty((map).mask, MAX_APICS)
+	bitmap_empty((map).mask, MAX_LOCAL_APIC)
 
 #define physids_equal(map1, map2)				\
-	bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+	bitmap_equal((map1).mask, (map2).mask, MAX_LOCAL_APIC)
 
 #define physids_weight(map)					\
-	bitmap_weight((map).mask, MAX_APICS)
+	bitmap_weight((map).mask, MAX_LOCAL_APIC)
 
 #define physids_shift_right(d, s, n)				\
-	bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+	bitmap_shift_right((d).mask, (s).mask, n, MAX_LOCAL_APIC)
 
 #define physids_shift_left(d, s, n)				\
-	bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+	bitmap_shift_left((d).mask, (s).mask, n, MAX_LOCAL_APIC)
 
 static inline unsigned long physids_coerce(physid_mask_t *map)
 {
@@ -159,14 +160,6 @@ static inline void physids_promote(unsigned long physids, physid_mask_t *map)
 	map->mask[0] = physids;
 }
 
-/* Note: will create very large stack frames if physid_mask_t is big */
-#define physid_mask_of_physid(physid)					\
-	({								\
-		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
-		physid_set(physid, __physid_mask);			\
-		__physid_mask;						\
-	})
-
 static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
 {
 	physids_clear(*map);
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 4a7f96d..c0a955a 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -15,13 +15,6 @@
 
 #ifdef CONFIG_X86_32
 # define MAX_MPC_ENTRY 1024
-# define MAX_APICS      256
-#else
-# if NR_CPUS <= 255
-#  define MAX_APICS     255
-# else
-#  define MAX_APICS   32768
-# endif
 #endif
 
 /* Intel MP Floating Pointer Structure */
diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/mrst-vrtc.h
new file mode 100644
index 0000000..73668ab
--- /dev/null
+++ b/arch/x86/include/asm/mrst-vrtc.h
@@ -0,0 +1,9 @@
+#ifndef _MRST_VRTC_H
+#define _MRST_VRTC_H
+
+extern unsigned char vrtc_cmos_read(unsigned char reg);
+extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
+extern unsigned long vrtc_get_time(void);
+extern int vrtc_set_mmss(unsigned long nowtime);
+
+#endif
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 4a711a6..719f00b 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -14,7 +14,9 @@
 #include <linux/sfi.h>
 
 extern int pci_mrst_init(void);
-int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int sfi_mrtc_num;
+extern struct sfi_rtc_table_entry sfi_mrtc_array[];
 
 /*
  * Medfield is the follow-up of Moorestown, it combines two chip solution into
@@ -50,4 +52,14 @@ extern void mrst_early_console_init(void);
 
 extern struct console early_hsu_console;
 extern void hsu_early_console_init(void);
+
+extern void intel_scu_devices_create(void);
+extern void intel_scu_devices_destroy(void);
+
+/* VRTC timer */
+#define MRST_VRTC_MAP_SZ	(1024)
+/*#define MRST_VRTC_PGOFFSET	(0xc00) */
+
+extern void mrst_rtc_init(void);
+
 #endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6b89f5e..4d0dfa0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -123,6 +123,10 @@
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
 
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTR		0xc0010201
+
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
 #define FAM10H_MMIO_CONF_ENABLE		(1<<0)
@@ -253,6 +257,18 @@
 #define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
 #define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
 
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
+#define THERM_SHIFT_THRESHOLD0        8
+#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
+#define THERM_SHIFT_THRESHOLD1        16
+#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0        (1 << 6)
+#define THERM_LOG_THRESHOLD0           (1 << 7)
+#define THERM_STATUS_THRESHOLD1        (1 << 8)
+#define THERM_LOG_THRESHOLD1           (1 << 9)
+
 /* MISC_ENABLE bits: architectural */
 #define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
 #define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 932f0f8..c76f5b9 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -5,41 +5,15 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
-/**
- * do_nmi_callback
- *
- * Check to see if a callback exists and execute it.  Return 1
- * if the handler exists and was handled successfully.
- */
-int do_nmi_callback(struct pt_regs *regs, int cpu);
+#ifdef CONFIG_X86_LOCAL_APIC
 
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern int check_nmi_watchdog(void);
-#if !defined(CONFIG_LOCKUP_DETECTOR)
-extern int nmi_watchdog_enabled;
-#endif
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-extern void setup_apic_nmi_watchdog(void *);
-extern void stop_apic_nmi_watchdog(void *);
-extern void disable_timer_nmi_watchdog(void);
-extern void enable_timer_nmi_watchdog(void);
-extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
-extern void cpu_nmi_set_wd_enabled(void);
-
-extern atomic_t nmi_active;
-extern unsigned int nmi_watchdog;
-#define NMI_NONE	0
-#define NMI_IO_APIC	1
-#define NMI_LOCAL_APIC	2
-#define NMI_INVALID	3
-
 struct ctl_table;
 extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
@@ -47,33 +21,28 @@ extern int unknown_nmi_panic;
 
 void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
 
-static inline void localise_nmi_watchdog(void)
-{
-	if (nmi_watchdog == NMI_IO_APIC)
-		nmi_watchdog = NMI_LOCAL_APIC;
-}
+/*
+ * Define some priorities for the nmi notifier call chain.
+ *
+ * Create a local nmi bit that has a higher priority than
+ * external nmis, because the local ones are more frequent.
+ *
+ * Also setup some default high/normal/low settings for
+ * subsystems to registers with.  Using 4 bits to seperate
+ * the priorities.  This can go alot higher if needed be.
+ */
 
-/* check if nmi_watchdog is active (ie was specified at boot) */
-static inline int nmi_watchdog_active(void)
-{
-	/*
-	 * actually it should be:
-	 * 	return (nmi_watchdog == NMI_LOCAL_APIC ||
-	 * 		nmi_watchdog == NMI_IO_APIC)
-	 * but since they are power of two we could use a
-	 * cheaper way --cvg
-	 */
-	return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
-}
-#endif
+#define NMI_LOCAL_SHIFT		16	/* randomly picked */
+#define NMI_LOCAL_BIT		(1ULL << NMI_LOCAL_SHIFT)
+#define NMI_HIGH_PRIOR		(1ULL << 8)
+#define NMI_NORMAL_PRIOR	(1ULL << 4)
+#define NMI_LOW_PRIOR		(1ULL << 0)
+#define NMI_LOCAL_HIGH_PRIOR	(NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
+#define NMI_LOCAL_NORMAL_PRIOR	(NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
+#define NMI_LOCAL_LOW_PRIOR	(NMI_LOCAL_BIT | NMI_LOW_PRIOR)
 
-void lapic_watchdog_stop(void);
-int lapic_watchdog_init(unsigned nmi_hz);
-int lapic_wd_event(unsigned nmi_hz);
-unsigned lapic_adjust_nmi_hz(unsigned hz);
-void disable_lapic_nmi_watchdog(void);
-void enable_lapic_nmi_watchdog(void);
 void stop_nmi(void);
 void restart_nmi(void);
 
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 823e070..5ae8728 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -38,7 +38,7 @@ extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
 
 #ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE	((u64)64 << 20)
+#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
 #endif /* CONFIG_NUMA_EMU */
 #else
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ef99758..7709c12 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -112,7 +112,7 @@ static inline void arch_safe_halt(void)
 
 static inline void halt(void)
 {
-	PVOP_VCALL0(pv_irq_ops.safe_halt);
+	PVOP_VCALL0(pv_irq_ops.halt);
 }
 
 static inline void wbinvd(void)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ca0437c..6761292 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -65,6 +65,7 @@ extern unsigned long pci_mem_start;
 
 #define PCIBIOS_MIN_CARDBUS_IO	0x4000
 
+extern int pcibios_enabled;
 void pcibios_config_init(void);
 struct pci_bus *pcibios_scan_root(int bus);
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index f899e01..8ee4516 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -230,6 +230,125 @@ do {									\
 })
 
 /*
+ * Add return operation
+ */
+#define percpu_add_return_op(var, val)					\
+({									\
+	typeof(var) paro_ret__ = val;					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("xaddb %0, "__percpu_arg(1)				\
+			    : "+q" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 2:								\
+		asm("xaddw %0, "__percpu_arg(1)				\
+			    : "+r" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 4:								\
+		asm("xaddl %0, "__percpu_arg(1)				\
+			    : "+r" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 8:								\
+		asm("xaddq %0, "__percpu_arg(1)				\
+			    : "+re" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	paro_ret__ += val;						\
+	paro_ret__;							\
+})
+
+/*
+ * xchg is implemented using cmpxchg without a lock prefix. xchg is
+ * expensive due to the implied lock prefix.  The processor cannot prefetch
+ * cachelines if xchg is used.
+ */
+#define percpu_xchg_op(var, nval)					\
+({									\
+	typeof(var) pxo_ret__;						\
+	typeof(var) pxo_new__ = (nval);					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("\n1:mov "__percpu_arg(1)",%%al"			\
+		    "\n\tcmpxchgb %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "q" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 2:								\
+		asm("\n1:mov "__percpu_arg(1)",%%ax"			\
+		    "\n\tcmpxchgw %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 4:								\
+		asm("\n1:mov "__percpu_arg(1)",%%eax"			\
+		    "\n\tcmpxchgl %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 8:								\
+		asm("\n1:mov "__percpu_arg(1)",%%rax"			\
+		    "\n\tcmpxchgq %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	pxo_ret__;							\
+})
+
+/*
+ * cmpxchg has no such implied lock semantics as a result it is much
+ * more efficient for cpu local operations.
+ */
+#define percpu_cmpxchg_op(var, oval, nval)				\
+({									\
+	typeof(var) pco_ret__;						\
+	typeof(var) pco_old__ = (oval);					\
+	typeof(var) pco_new__ = (nval);					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("cmpxchgb %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "q" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 2:								\
+		asm("cmpxchgw %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 4:								\
+		asm("cmpxchgl %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 8:								\
+		asm("cmpxchgq %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	pco_ret__;							\
+})
+
+/*
  * percpu_read() makes gcc load the percpu variable every time it is
  * accessed while percpu_read_stable() allows the value to be cached.
  * percpu_read_stable() is more efficient and can be used if its value
@@ -267,6 +386,12 @@ do {									\
 #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)
+/*
+ * Generic fallback operations for __this_cpu_xchg_[1-4] are okay and much
+ * faster than an xchg with forced lock semantics.
+ */
+#define __this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define __this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 #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))
@@ -286,6 +411,11 @@ do {									\
 #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_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 #define irqsafe_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
 #define irqsafe_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
@@ -299,6 +429,31 @@ do {									\
 #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)
+#define irqsafe_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
+#ifndef CONFIG_M386
+#define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
+#define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
+#define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
+#define __this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define __this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define __this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
+#define this_cpu_add_return_1(pcp, val)	percpu_add_return_op(pcp, val)
+#define this_cpu_add_return_2(pcp, val)	percpu_add_return_op(pcp, val)
+#define this_cpu_add_return_4(pcp, val)	percpu_add_return_op(pcp, val)
+#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
+#define irqsafe_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#endif /* !CONFIG_M386 */
 
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -311,6 +466,7 @@ do {									\
 #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_add_return_8(pcp, val) percpu_add_return_op(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)
@@ -318,12 +474,12 @@ do {									\
 #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_add_return_8(pcp, val)	percpu_add_return_op(pcp, val)
 
 #define irqsafe_cpu_add_8(pcp, val)	percpu_add_op((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 */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 550e26b1..d9d4dae 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -125,7 +125,6 @@ union cpuid10_edx {
 #define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
 
 #ifdef CONFIG_PERF_EVENTS
-extern void init_hw_perf_events(void);
 extern void perf_events_lapic_init(void);
 
 #define PERF_EVENT_INDEX_OFFSET			0
@@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 }
 
 #else
-static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index a70cd21..e2f6a99 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -20,6 +20,9 @@
 #define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
 #define ARCH_P4_MAX_CCCR	(18)
 
+#define ARCH_P4_CNTRVAL_BITS	(40)
+#define ARCH_P4_CNTRVAL_MASK	((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+
 #define P4_ESCR_EVENT_MASK	0x7e000000U
 #define P4_ESCR_EVENT_SHIFT	25
 #define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
@@ -744,14 +747,6 @@ enum P4_ESCR_EMASKS {
 };
 
 /*
- * P4 PEBS specifics (Replay Event only)
- *
- * Format (bits):
- *   0-6: metric from P4_PEBS_METRIC enum
- *    7 : reserved
- *    8 : reserved
- * 9-11 : reserved
- *
  * Note we have UOP and PEBS bits reserved for now
  * just in case if we will need them once
  */
@@ -788,5 +783,60 @@ enum P4_PEBS_METRIC {
 	P4_PEBS_METRIC__max
 };
 
+/*
+ * Notes on internal configuration of ESCR+CCCR tuples
+ *
+ * Since P4 has quite the different architecture of
+ * performance registers in compare with "architectural"
+ * once and we have on 64 bits to keep configuration
+ * of performance event, the following trick is used.
+ *
+ * 1) Since both ESCR and CCCR registers have only low
+ *    32 bits valuable, we pack them into a single 64 bit
+ *    configuration. Low 32 bits of such config correspond
+ *    to low 32 bits of CCCR register and high 32 bits
+ *    correspond to low 32 bits of ESCR register.
+ *
+ * 2) The meaning of every bit of such config field can
+ *    be found in Intel SDM but it should be noted that
+ *    we "borrow" some reserved bits for own usage and
+ *    clean them or set to a proper value when we do
+ *    a real write to hardware registers.
+ *
+ * 3) The format of bits of config is the following
+ *    and should be either 0 or set to some predefined
+ *    values:
+ *
+ *    Low 32 bits
+ *    -----------
+ *      0-6: P4_PEBS_METRIC enum
+ *     7-11:                    reserved
+ *       12:                    reserved (Enable)
+ *    13-15:                    reserved (ESCR select)
+ *    16-17: Active Thread
+ *       18: Compare
+ *       19: Complement
+ *    20-23: Threshold
+ *       24: Edge
+ *       25:                    reserved (FORCE_OVF)
+ *       26:                    reserved (OVF_PMI_T0)
+ *       27:                    reserved (OVF_PMI_T1)
+ *    28-29:                    reserved
+ *       30:                    reserved (Cascade)
+ *       31:                    reserved (OVF)
+ *
+ *    High 32 bits
+ *    ------------
+ *        0:                    reserved (T1_USR)
+ *        1:                    reserved (T1_OS)
+ *        2:                    reserved (T0_USR)
+ *        3:                    reserved (T0_OS)
+ *        4: Tag Enable
+ *      5-8: Tag Value
+ *     9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper)
+ *    25-30: enum P4_EVENTS
+ *       31:                    reserved (HT thread)
+ */
+
 #endif /* PERF_EVENT_P4_H */
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b79bd98..521acfc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -141,10 +141,9 @@ extern __u32			cpu_caps_set[NCAPINTS];
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)		per_cpu(cpu_info, cpu)
-#define current_cpu_data	__get_cpu_var(cpu_info)
 #else
+#define cpu_info		boot_cpu_data
 #define cpu_data(cpu)		boot_cpu_data
-#define current_cpu_data	boot_cpu_data
 #endif
 
 extern const struct seq_operations cpuinfo_op;
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index d6763b139a..db8aa19 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -53,6 +53,12 @@ extern void x86_mrst_early_setup(void);
 static inline void x86_mrst_early_setup(void) { }
 #endif
 
+#ifdef CONFIG_X86_INTEL_CE
+extern void x86_ce4100_early_setup(void);
+#else
+static inline void x86_ce4100_early_setup(void) { }
+#endif
+
 #ifndef _SETUP
 
 /*
diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 1def601..6c22bf3 100644
--- a/arch/x86/include/asm/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void)
 		setup_IO_APIC();
 	else {
 		nr_ioapics = 0;
-		localise_nmi_watchdog();
 	}
 #endif
 }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 2b16a2a..52b5c7e 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -7,6 +7,7 @@
 #define _ASM_X86_STACKTRACE_H
 
 #include <linux/uaccess.h>
+#include <linux/ptrace.h>
 
 extern int kstack_depth_to_print;
 
@@ -46,7 +47,7 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
+		unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data);
 
 #ifdef CONFIG_X86_32
@@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	unsigned long bp;
+
+	if (regs)
+		return regs->bp;
+
+	if (task == current) {
+		/* Grab bp right from our regs */
+		get_bp(bp);
+		return bp;
+	}
+
+	/* bp is the last reg pushed by switch_to */
+	return *(unsigned long *)task->thread.sp;
+}
+#else
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	return 0;
+}
+#endif
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl);
+		   unsigned long *stack, char *log_lvl);
 
 extern void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *sp, unsigned long bp, char *log_lvl);
+		   unsigned long *sp, char *log_lvl);
 
 extern unsigned int code_bytes;
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 5469630..fa7b917 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -10,12 +10,6 @@
 unsigned long long native_sched_clock(void);
 extern int recalibrate_cpu_khz(void);
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-extern int timer_ack;
-#else
-# define timer_ack (0)
-#endif
-
 extern int no_timer_check;
 
 /* Accelerators for sched_clock()
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 42d412f..ce1d54c 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -26,20 +26,22 @@
  * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
  * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
  *
- * We will use 31 sets, one for sending BAU messages from each of the 32
+ * We will use one set for sending BAU messages from each of the
  * cpu's on the uvhub.
  *
  * TLB shootdown will use the first of the 8 descriptors of each set.
  * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
  */
 
+#define MAX_CPUS_PER_UVHUB		64
+#define MAX_CPUS_PER_SOCKET		32
+#define UV_ADP_SIZE			64 /* hardware-provided max. */
+#define UV_CPUS_PER_ACT_STATUS		32 /* hardware-provided max. */
 #define UV_ITEMS_PER_DESCRIPTOR		8
 /* the 'throttle' to prevent the hardware stay-busy bug */
 #define MAX_BAU_CONCURRENT		3
-#define UV_CPUS_PER_ACT_STATUS		32
 #define UV_ACT_STATUS_MASK		0x3
 #define UV_ACT_STATUS_SIZE		2
-#define UV_ADP_SIZE			32
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
 #define UV_NET_ENDPOINT_INTD		0x38
@@ -100,7 +102,6 @@
  * number of destination side software ack resources
  */
 #define DEST_NUM_RESOURCES		8
-#define MAX_CPUS_PER_NODE		32
 /*
  * completion statuses for sending a TLB flush message
  */
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 396ff4c..66d0fff 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,4 +37,39 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
+#include <asm/processor.h>
+
+static inline uint32_t xen_cpuid_base(void)
+{
+	uint32_t base, eax, ebx, ecx, edx;
+	char signature[13];
+
+	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+		cpuid(base, &eax, &ebx, &ecx, &edx);
+		*(uint32_t *)(signature + 0) = ebx;
+		*(uint32_t *)(signature + 4) = ecx;
+		*(uint32_t *)(signature + 8) = edx;
+		signature[12] = 0;
+
+		if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
+			return base;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_XEN
+extern bool xen_hvm_need_lapic(void);
+
+static inline bool xen_x2apic_para_available(void)
+{
+	return xen_hvm_need_lapic();
+}
+#else
+static inline bool xen_x2apic_para_available(void)
+{
+	return (xen_cpuid_base() != 0);
+}
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */