Merge branch 'linus' into idle-test

135 files changed, 3453 insertions, 2692 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e330da21b84f..b6fccb07123e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -377,6 +377,18 @@ config X86_ELAN
 
           If unsure, choose "PC-compatible" instead.
 
+config X86_INTEL_CE
+        bool "CE4100 TV platform"
+        depends on PCI
+        depends on PCI_GODIRECT
+        depends on X86_32
+        depends on X86_EXTENDED_PLATFORM
+        select X86_REBOOTFIXUPS
+        ---help---
+          Select for the Intel CE media processor (CE4100) SOC.
+          This option compiles in support for the CE4100 SOC for settop
+          boxes and media devices.
+
 config X86_MRST
        bool "Moorestown MID platform"
         depends on PCI
@@ -385,6 +397,10 @@ config X86_MRST
         depends on X86_EXTENDED_PLATFORM
         depends on X86_IO_APIC
         select APB_TIMER
+        select I2C
+        select SPI
+        select INTEL_SCU_IPC
+        select X86_PLATFORM_DEVICES
         ---help---
           Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
           Internet Device(MID) platform. Moorestown consists of two chips:
@@ -466,6 +482,19 @@ config X86_ES7000
           Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
           supposed to run on an IA32-based Unisys ES7000 system.
 
+config X86_32_IRIS
+        tristate "Eurobraille/Iris poweroff module"
+        depends on X86_32
+        ---help---
+          The Iris machines from EuroBraille do not have APM or ACPI support
+          to shut themselves down properly.  A special I/O sequence is
+          needed to do so, which is what this module does at
+          kernel shutdown.
+
+          This is only for Iris machines from EuroBraille.
+
+          If unused, say N.
+
 config SCHED_OMIT_FRAME_POINTER
         def_bool y
         prompt "Single-depth WCHAN output"
@@ -1141,16 +1170,16 @@ config NUMA
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
         depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
 
-config K8_NUMA
+config AMD_NUMA
         def_bool y
         prompt "Old style AMD Opteron NUMA detection"
         depends on X86_64 && NUMA && PCI
         ---help---
-          Enable K8 NUMA node topology detection.  You should say Y here if
-          you have a multi processor AMD K8 system. This uses an old
-          method to read the NUMA configuration directly from the builtin
-          Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA
-          instead, which also takes priority if both are compiled in.
+          Enable AMD NUMA node topology detection.  You should say Y here if
+          you have a multi processor AMD system. This uses an old method to
+          read the NUMA configuration directly from the builtin Northbridge
+          of Opteron. It is recommended to use X86_64_ACPI_NUMA instead,
+          which also takes priority if both are compiled in.
 
 config X86_64_ACPI_NUMA
         def_bool y
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2ac9069890cd..15588a0ef466 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -310,6 +310,9 @@ config X86_INTERNODE_CACHE_SHIFT
 config X86_CMPXCHG
         def_bool X86_64 || (X86_32 && !M386)
 
+config CMPXCHG_LOCAL
+        def_bool X86_64 || (X86_32 && !M386)
+
 config X86_L1_CACHE_SHIFT
         int
         default "7" if MPENTIUM4 || MPSC
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index b59ee765414e..45143bbcfe5e 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -117,6 +117,17 @@ config DEBUG_RODATA_TEST
           feature as well as for the change_page_attr() infrastructure.
           If in doubt, say "N"
 
+config DEBUG_SET_MODULE_RONX
+        bool "Set loadable kernel module data as NX and text as RO"
+        depends on MODULES
+        ---help---
+          This option helps catch unintended modifications to loadable
+          kernel module's text and read-only data. It also prevents execution
+          of module data. Such protection may interfere with run-time code
+          patching and dynamic kernel tracing - and they might also protect
+          against certain classes of kernel exploits.
+          If in doubt, say "N".
+
 config DEBUG_NX_TEST
         tristate "Testcase for the NX non-executable stack feature"
         depends on DEBUG_KERNEL && m
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 52f85a196fa0..35af09d13dc1 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -182,7 +182,7 @@ no_longmode:
         hlt
         jmp     1b
 
-#include "../../kernel/verify_cpu_64.S"
+#include "../../kernel/verify_cpu.S"
 
         /*
          * Be careful here startup_64 needs to be at a predictable
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 55d106b5e31b..211ca3f7fd16 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 76561d20ea2f..13009d1af99a 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 c8517f81b21e..64dc82ee19f0 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 f6ce0bda3b98..5e3969c36d7f 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 a859ca461fb0..47a30ff8e517 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 8e6218550e77..c8bfe63a06de 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 b81002f23614..078ad0caefc6 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 9479a037419f..4729b2b63117 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 49dbfdfa50f9..91d915a65259 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 ff2546ce7178..7a15153c675d 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 4aa2bb3b242a..ef328901c802 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 a6b28d017c2f..f327d386d6cc 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 13b0ebaa512f..ba870bb6dd8e 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 5bdfca86581b..ca242d35e873 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 f7920601e472..72a8b52e7dfd 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 c62c13cb9788..eb16e94ae04f 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 ef51b501e22a..24215072d0e1 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 c82868e9f905..0c90dd9f0505 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 4a7f96d7c188..c0a955a9a087 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 000000000000..73668abdbedf
--- /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 4a711a684b17..719f00b28ff5 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 6b89f5e86021..4d0dfa0d998e 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 932f0f86b4b7..c76f5b92b840 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 823e070e7c26..5ae87285a502 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 ef9975812c77..7709c12431b8 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 ca0437c714b2..676129229630 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 f899e01a8ac9..8ee45167e817 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 550e26b1dbb3..d9d4dae305f6 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 a70cd216be5d..e2f6a99f14ab 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 b79bd980461c..521acfc47e7d 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 d6763b139a84..db8aa19a08a2 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 1def60114906..6c22bf353f26 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 2b16a2ad23dc..52b5c7ed3608 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 5469630b27f5..fa7b9176b76c 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 42d412fd8b02..ce1d54c8a433 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 396ff4cc8ed4..66d0fff1ee84 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 */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 1e994754d323..34244b2cd880 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -85,7 +85,6 @@ obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)              += kgdb.o
 obj-$(CONFIG_VM86)              += vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)      += early_printk.o
-obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o
 
 obj-$(CONFIG_HPET_TIMER)        += hpet.o
 obj-$(CONFIG_APB_TIMER)         += apb_timer.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 71232b941b6c..ec881c6bfee0 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
         unsigned int ver = 0;
 
+        if (id >= (MAX_LOCAL_APIC-1)) {
+                printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
+                return;
+        }
+
         if (!enabled) {
                 ++disabled_cpus;
                 return;
@@ -847,18 +852,6 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
  * returns 0 on success, < 0 on error
  */
 
-static void __init acpi_register_lapic_address(unsigned long address)
-{
-        mp_lapic_addr = address;
-
-        set_fixmap_nocache(FIX_APIC_BASE, address);
-        if (boot_cpu_physical_apicid == -1U) {
-                boot_cpu_physical_apicid  = read_apic_id();
-                apic_version[boot_cpu_physical_apicid] =
-                         GET_APIC_VERSION(apic_read(APIC_LVR));
-        }
-}
-
 static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 {
         int count;
@@ -880,7 +873,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
                 return count;
         }
 
-        acpi_register_lapic_address(acpi_lapic_addr);
+        register_lapic_address(acpi_lapic_addr);
 
         return count;
 }
@@ -907,16 +900,16 @@ static int __init acpi_parse_madt_lapic_entries(void)
                 return count;
         }
 
-        acpi_register_lapic_address(acpi_lapic_addr);
+        register_lapic_address(acpi_lapic_addr);
 
         count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
-                                      acpi_parse_sapic, MAX_APICS);
+                                      acpi_parse_sapic, MAX_LOCAL_APIC);
 
         if (!count) {
                 x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
-                                                acpi_parse_x2apic, MAX_APICS);
+                                        acpi_parse_x2apic, MAX_LOCAL_APIC);
                 count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
-                                              acpi_parse_lapic, MAX_APICS);
+                                        acpi_parse_lapic, MAX_LOCAL_APIC);
         }
         if (!count && !x2count) {
                 printk(KERN_ERR PREFIX "No LAPIC entries present\n");
@@ -949,32 +942,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
 extern int es7000_plat;
 #endif
 
-static void assign_to_mp_irq(struct mpc_intsrc *m,
-                                    struct mpc_intsrc *mp_irq)
-{
-        memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
-}
-
-static int mp_irq_cmp(struct mpc_intsrc *mp_irq,
-                                struct mpc_intsrc *m)
-{
-        return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
-}
-
-static void save_mp_irq(struct mpc_intsrc *m)
-{
-        int i;
-
-        for (i = 0; i < mp_irq_entries; i++) {
-                if (!mp_irq_cmp(&mp_irqs[i], m))
-                        return;
-        }
-
-        assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
-        if (++mp_irq_entries == MAX_IRQ_SOURCES)
-                panic("Max # of irq sources exceeded!!\n");
-}
-
 void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
 {
         int ioapic;
@@ -1005,7 +972,7 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
         mp_irq.dstapic = mp_ioapics[ioapic].apicid; /* APIC ID */
         mp_irq.dstirq = pin;    /* INTIN# */
 
-        save_mp_irq(&mp_irq);
+        mp_save_irq(&mp_irq);
 
         isa_irq_to_gsi[bus_irq] = gsi;
 }
@@ -1080,7 +1047,7 @@ void __init mp_config_acpi_legacy_irqs(void)
                 mp_irq.srcbusirq = i; /* Identity mapped */
                 mp_irq.dstirq = pin;
 
-                save_mp_irq(&mp_irq);
+                mp_save_irq(&mp_irq);
         }
 }
 
@@ -1117,7 +1084,7 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
         mp_irq.dstapic = mp_ioapics[ioapic].apicid;
         mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
 
-        save_mp_irq(&mp_irq);
+        mp_save_irq(&mp_irq);
 #endif
         return 0;
 }
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5079f24c955a..123608531c8f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
         mutex_unlock(&smp_alt);
 }
 
+bool skip_smp_alternatives;
 void alternatives_smp_switch(int smp)
 {
         struct smp_alt_module *mod;
@@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp)
         printk("lockdep: fixing up alternatives.\n");
 #endif
 
-        if (noreplace_smp || smp_alt_once)
+        if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
                 return;
         BUG_ON(!smp && (num_online_cpus() > 1));
 
@@ -591,17 +592,21 @@ static atomic_t stop_machine_first;
 static int wrote_text;
 
 struct text_poke_params {
-        void *addr;
-        const void *opcode;
-        size_t len;
+        struct text_poke_param *params;
+        int nparams;
 };
 
 static int __kprobes stop_machine_text_poke(void *data)
 {
         struct text_poke_params *tpp = data;
+        struct text_poke_param *p;
+        int i;
 
         if (atomic_dec_and_test(&stop_machine_first)) {
-                text_poke(tpp->addr, tpp->opcode, tpp->len);
+                for (i = 0; i < tpp->nparams; i++) {
+                        p = &tpp->params[i];
+                        text_poke(p->addr, p->opcode, p->len);
+                }
                 smp_wmb();      /* Make sure other cpus see that this has run */
                 wrote_text = 1;
         } else {
@@ -610,8 +615,12 @@ static int __kprobes stop_machine_text_poke(void *data)
                 smp_mb();       /* Load wrote_text before following execution */
         }
 
-        flush_icache_range((unsigned long)tpp->addr,
-                           (unsigned long)tpp->addr + tpp->len);
+        for (i = 0; i < tpp->nparams; i++) {
+                p = &tpp->params[i];
+                flush_icache_range((unsigned long)p->addr,
+                                   (unsigned long)p->addr + p->len);
+        }
+
         return 0;
 }
 
@@ -631,10 +640,13 @@ static int __kprobes stop_machine_text_poke(void *data)
 void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 {
         struct text_poke_params tpp;
+        struct text_poke_param p;
 
-        tpp.addr = addr;
-        tpp.opcode = opcode;
-        tpp.len = len;
+        p.addr = addr;
+        p.opcode = opcode;
+        p.len = len;
+        tpp.params = &p;
+        tpp.nparams = 1;
         atomic_set(&stop_machine_first, 1);
         wrote_text = 0;
         /* Use __stop_machine() because the caller already got online_cpus. */
@@ -642,6 +654,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
         return addr;
 }
 
+/**
+ * text_poke_smp_batch - Update instructions on a live kernel on SMP
+ * @params: an array of text_poke parameters
+ * @n: the number of elements in params.
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. Since the
+ * stop_machine() is heavy task, it is better to aggregate text_poke requests
+ * and do it once if possible.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+{
+        struct text_poke_params tpp = {.params = params, .nparams = n};
+
+        atomic_set(&stop_machine_first, 1);
+        wrote_text = 0;
+        stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+}
+
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 8f6463d8ed0d..0a99f7198bc3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -12,95 +12,123 @@
 
 static u32 *flush_words;
 
-struct pci_device_id k8_nb_ids[] = {
+struct pci_device_id amd_nb_misc_ids[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
         {}
 };
-EXPORT_SYMBOL(k8_nb_ids);
+EXPORT_SYMBOL(amd_nb_misc_ids);
 
-struct k8_northbridge_info k8_northbridges;
-EXPORT_SYMBOL(k8_northbridges);
+const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
+        { 0x00, 0x18, 0x20 },
+        { 0xff, 0x00, 0x20 },
+        { 0xfe, 0x00, 0x20 },
+        { }
+};
+
+struct amd_northbridge_info amd_northbridges;
+EXPORT_SYMBOL(amd_northbridges);
 
-static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
+static struct pci_dev *next_northbridge(struct pci_dev *dev,
+                                        struct pci_device_id *ids)
 {
         do {
                 dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
                 if (!dev)
                         break;
-        } while (!pci_match_id(&k8_nb_ids[0], dev));
+        } while (!pci_match_id(ids, dev));
         return dev;
 }
 
-int cache_k8_northbridges(void)
+int amd_cache_northbridges(void)
 {
-        int i;
-        struct pci_dev *dev;
+        int i = 0;
+        struct amd_northbridge *nb;
+        struct pci_dev *misc;
 
-        if (k8_northbridges.num)
+        if (amd_nb_num())
                 return 0;
 
-        dev = NULL;
-        while ((dev = next_k8_northbridge(dev)) != NULL)
-                k8_northbridges.num++;
+        misc = NULL;
+        while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+                i++;
 
-        /* some CPU families (e.g. family 0x11) do not support GART */
-        if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-            boot_cpu_data.x86 == 0x15)
-                k8_northbridges.gart_supported = 1;
+        if (i == 0)
+                return 0;
 
-        k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
-                                          sizeof(void *), GFP_KERNEL);
-        if (!k8_northbridges.nb_misc)
+        nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
+        if (!nb)
                 return -ENOMEM;
 
-        if (!k8_northbridges.num) {
-                k8_northbridges.nb_misc[0] = NULL;
-                return 0;
-        }
+        amd_northbridges.nb = nb;
+        amd_northbridges.num = i;
 
-        if (k8_northbridges.gart_supported) {
-                flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
-                                      GFP_KERNEL);
-                if (!flush_words) {
-                        kfree(k8_northbridges.nb_misc);
-                        return -ENOMEM;
-                }
-        }
+        misc = NULL;
+        for (i = 0; i != amd_nb_num(); i++) {
+                node_to_amd_nb(i)->misc = misc =
+                        next_northbridge(misc, amd_nb_misc_ids);
+        }
+
+        /* some CPU families (e.g. family 0x11) do not support GART */
+        if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+            boot_cpu_data.x86 == 0x15)
+                amd_northbridges.flags |= AMD_NB_GART;
+
+        /*
+         * Some CPU families support L3 Cache Index Disable. There are some
+         * limitations because of E382 and E388 on family 0x10.
+         */
+        if (boot_cpu_data.x86 == 0x10 &&
+            boot_cpu_data.x86_model >= 0x8 &&
+            (boot_cpu_data.x86_model > 0x9 ||
+             boot_cpu_data.x86_mask >= 0x1))
+                amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
 
-        dev = NULL;
-        i = 0;
-        while ((dev = next_k8_northbridge(dev)) != NULL) {
-                k8_northbridges.nb_misc[i] = dev;
-                if (k8_northbridges.gart_supported)
-                        pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
-        }
-        k8_northbridges.nb_misc[i] = NULL;
         return 0;
 }
-EXPORT_SYMBOL_GPL(cache_k8_northbridges);
+EXPORT_SYMBOL_GPL(amd_cache_northbridges);
 
 /* Ignores subdevice/subvendor but as far as I can figure out
    they're useless anyways */
-int __init early_is_k8_nb(u32 device)
+int __init early_is_amd_nb(u32 device)
 {
         struct pci_device_id *id;
         u32 vendor = device & 0xffff;
         device >>= 16;
-        for (id = k8_nb_ids; id->vendor; id++)
+        for (id = amd_nb_misc_ids; id->vendor; id++)
                 if (vendor == id->vendor && device == id->device)
                         return 1;
         return 0;
 }
 
-void k8_flush_garts(void)
+int amd_cache_gart(void)
+{
+       int i;
+
+       if (!amd_nb_has_feature(AMD_NB_GART))
+               return 0;
+
+       flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+       if (!flush_words) {
+               amd_northbridges.flags &= ~AMD_NB_GART;
+               return -ENOMEM;
+       }
+
+       for (i = 0; i != amd_nb_num(); i++)
+               pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+                                     &flush_words[i]);
+
+       return 0;
+}
+
+void amd_flush_garts(void)
 {
         int flushed, i;
         unsigned long flags;
         static DEFINE_SPINLOCK(gart_lock);
 
-        if (!k8_northbridges.gart_supported)
+        if (!amd_nb_has_feature(AMD_NB_GART))
                 return;
 
         /* Avoid races between AGP and IOMMU. In theory it's not needed
@@ -109,16 +137,16 @@ void k8_flush_garts(void)
            that it doesn't matter to serialize more. -AK */
         spin_lock_irqsave(&gart_lock, flags);
         flushed = 0;
-        for (i = 0; i < k8_northbridges.num; i++) {
-                pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
-                                       flush_words[i]|1);
+        for (i = 0; i < amd_nb_num(); i++) {
+                pci_write_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+                                       flush_words[i] | 1);
                 flushed++;
         }
-        for (i = 0; i < k8_northbridges.num; i++) {
+        for (i = 0; i < amd_nb_num(); i++) {
                 u32 w;
                 /* Make sure the hardware actually executed the flush*/
                 for (;;) {
-                        pci_read_config_dword(k8_northbridges.nb_misc[i],
+                        pci_read_config_dword(node_to_amd_nb(i)->misc,
                                               0x9c, &w);
                         if (!(w & 1))
                                 break;
@@ -129,19 +157,23 @@ void k8_flush_garts(void)
         if (!flushed)
                 printk("nothing to flush?\n");
 }
-EXPORT_SYMBOL_GPL(k8_flush_garts);
+EXPORT_SYMBOL_GPL(amd_flush_garts);
 
-static __init int init_k8_nbs(void)
+static __init int init_amd_nbs(void)
 {
         int err = 0;
 
-        err = cache_k8_northbridges();
+        err = amd_cache_northbridges();
 
         if (err < 0)
-                printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n");
+                printk(KERN_NOTICE "AMD NB: Cannot enumerate AMD northbridges.\n");
+
+        if (amd_cache_gart() < 0)
+                printk(KERN_NOTICE "AMD NB: Cannot initialize GART flush words, "
+                       "GART support disabled.\n");
 
         return err;
 }
 
 /* This has to go after the PCI subsystem */
-fs_initcall(init_k8_nbs);
+fs_initcall(init_amd_nbs);
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 92543c73cf8e..7c9ab59653e8 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -315,6 +315,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
 
         if (system_state == SYSTEM_BOOTING) {
                 irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+                irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
                 /* APB timer irqs are set up as mp_irqs, timer is edge type */
                 __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
                 if (request_irq(adev->irq, apbt_interrupt_handler,
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index b3a16e8f0703..5955a7800a96 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -39,18 +39,6 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
-struct bus_dev_range {
-        int bus;
-        int dev_base;
-        int dev_limit;
-};
-
-static struct bus_dev_range bus_dev_ranges[] __initdata = {
-        { 0x00, 0x18, 0x20},
-        { 0xff, 0x00, 0x20},
-        { 0xfe, 0x00, 0x20}
-};
-
 static struct resource gart_resource = {
         .name   = "GART",
         .flags  = IORESOURCE_MEM,
@@ -206,7 +194,7 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
  * Do an PCI bus scan by hand because we're running before the PCI
  * subsystem.
  *
- * All K8 AGP bridges are AGPv3 compliant, so we can do this scan
+ * All AMD AGP bridges are AGPv3 compliant, so we can do this scan
  * generically. It's probably overkill to always scan all slots because
  * the AGP bridges should be always an own bus on the HT hierarchy,
  * but do it here for future safety.
@@ -294,16 +282,16 @@ void __init early_gart_iommu_check(void)
         search_agp_bridge(&agp_aper_order, &valid_agp);
 
         fix = 0;
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
-                        if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+                        if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
 
                         ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -349,16 +337,16 @@ void __init early_gart_iommu_check(void)
                 return;
 
         /* disable them all at first */
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
-                        if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+                        if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
 
                         ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -390,17 +378,17 @@ int __init gart_iommu_hole_init(void)
 
         fix = 0;
         node = 0;
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
                 u32 ctl;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
-                        if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+                        if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
 
                         iommu_detected = 1;
@@ -505,7 +493,7 @@ out:
         }
 
         /* Fix up the north bridges */
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus, dev_base, dev_limit;
 
                 /*
@@ -514,11 +502,11 @@ out:
                  */
                 u32 ctl = DISTLBWALKPRB | aper_order << 1;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
                 for (slot = dev_base; slot < dev_limit; slot++) {
-                        if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+                        if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
 
                         write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 910f20b457c4..3966b564ea47 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -3,10 +3,7 @@
 #
 
 obj-$(CONFIG_X86_LOCAL_APIC)    += apic.o apic_noop.o probe_$(BITS).o ipi.o
-ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
-obj-$(CONFIG_X86_LOCAL_APIC)    += nmi.o
-endif
-obj-$(CONFIG_HARDLOCKUP_DETECTOR)       += hw_nmi.o
+obj-y                           += hw_nmi.o
 
 obj-$(CONFIG_X86_IO_APIC)       += io_apic.o
 obj-$(CONFIG_SMP)               += ipi.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 78218135b48e..06c196d7e59c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -31,7 +31,6 @@
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/dmi.h>
-#include <linux/nmi.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
 
@@ -50,8 +49,8 @@
 #include <asm/mtrr.h>
 #include <asm/smp.h>
 #include <asm/mce.h>
-#include <asm/kvm_para.h>
 #include <asm/tsc.h>
+#include <asm/hypervisor.h>
 
 unsigned int num_processors;
 
@@ -432,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
         reserved = reserve_eilvt_offset(offset, new);
 
         if (reserved != new) {
-                pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
-                       "vector 0x%x was already reserved by another core, "
-                       "APIC%lX=0x%x\n",
-                       smp_processor_id(), new, reserved, reg, old);
+                pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+                       "vector 0x%x, but the register is already in use for "
+                       "vector 0x%x on another cpu\n",
+                       smp_processor_id(), reg, offset, new, reserved);
                 return -EINVAL;
         }
 
         if (!eilvt_entry_is_changeable(old, new)) {
-                pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
-                       "register already in use, APIC%lX=0x%x\n",
-                       smp_processor_id(), new, reg, old);
+                pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+                       "vector 0x%x, but the register is already in use for "
+                       "vector 0x%x on this cpu\n",
+                       smp_processor_id(), reg, offset, new, old);
                 return -EBUSY;
         }
 
@@ -516,7 +516,7 @@ static void __cpuinit setup_APIC_timer(void)
 {
         struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-        if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
+        if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) {
                 lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
                 /* Make LAPIC timer preferrable over percpu HPET */
                 lapic_clockevent.rating = 150;
@@ -684,7 +684,7 @@ static int __init calibrate_APIC_clock(void)
         lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
                                        lapic_clockevent.shift);
         lapic_clockevent.max_delta_ns =
-                clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+                clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
         lapic_clockevent.min_delta_ns =
                 clockevent_delta2ns(0xF, &lapic_clockevent);
 
@@ -799,11 +799,7 @@ void __init setup_boot_APIC_clock(void)
          * PIT/HPET going.  Otherwise register lapic as a dummy
          * device.
          */
-        if (nmi_watchdog != NMI_IO_APIC)
-                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-        else
-                pr_warning("APIC timer registered as dummy,"
-                        " due to nmi_watchdog=%d!\n", nmi_watchdog);
+        lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 
         /* Setup the lapic or request the broadcast */
         setup_APIC_timer();
@@ -1195,12 +1191,15 @@ static void __cpuinit lapic_setup_esr(void)
                         oldvalue, value);
 }
 
-
 /**
  * setup_local_APIC - setup the local APIC
+ *
+ * Used to setup local APIC while initializing BSP or bringin up APs.
+ * Always called with preemption disabled.
  */
 void __cpuinit setup_local_APIC(void)
 {
+        int cpu = smp_processor_id();
         unsigned int value, queued;
         int i, j, acked = 0;
         unsigned long long tsc = 0, ntsc;
@@ -1225,8 +1224,6 @@ void __cpuinit setup_local_APIC(void)
 #endif
         perf_events_lapic_init();
 
-        preempt_disable();
-
         /*
          * Double-check whether this APIC is really registered.
          * This is meaningless in clustered apic mode, so we skip it.
@@ -1342,21 +1339,19 @@ void __cpuinit setup_local_APIC(void)
          * TODO: set up through-local-APIC from through-I/O-APIC? --macro
          */
         value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
-        if (!smp_processor_id() && (pic_mode || !value)) {
+        if (!cpu && (pic_mode || !value)) {
                 value = APIC_DM_EXTINT;
-                apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n",
-                                smp_processor_id());
+                apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu);
         } else {
                 value = APIC_DM_EXTINT | APIC_LVT_MASKED;
-                apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n",
-                                smp_processor_id());
+                apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n", cpu);
         }
         apic_write(APIC_LVT0, value);
 
         /*
          * only the BP should see the LINT1 NMI signal, obviously.
          */
-        if (!smp_processor_id())
+        if (!cpu)
                 value = APIC_DM_NMI;
         else
                 value = APIC_DM_NMI | APIC_LVT_MASKED;
@@ -1364,11 +1359,9 @@ void __cpuinit setup_local_APIC(void)
                 value |= APIC_LVT_LEVEL_TRIGGER;
         apic_write(APIC_LVT1, value);
 
-        preempt_enable();
-
 #ifdef CONFIG_X86_MCE_INTEL
         /* Recheck CMCI information after local APIC is up on CPU #0 */
-        if (smp_processor_id() == 0)
+        if (!cpu)
                 cmci_recheck();
 #endif
 }
@@ -1387,7 +1380,6 @@ void __cpuinit end_local_APIC_setup(void)
         }
 #endif
 
-        setup_apic_nmi_watchdog(NULL);
         apic_pm_activate();
 
         /*
@@ -1484,7 +1476,8 @@ void __init enable_IR_x2apic(void)
                 /* IR is required if there is APIC ID > 255 even when running
                  * under KVM
                  */
-                if (max_physical_apicid > 255 || !kvm_para_available())
+                if (max_physical_apicid > 255 ||
+                    !hypervisor_x2apic_available())
                         goto nox2apic;
                 /*
                  * without IR all CPUs can be addressed by IOAPIC/MSI
@@ -1538,13 +1531,60 @@ static int __init detect_init_APIC(void)
         return 0;
 }
 #else
+
+static int apic_verify(void)
+{
+        u32 features, h, l;
+
+        /*
+         * The APIC feature bit should now be enabled
+         * in `cpuid'
+         */
+        features = cpuid_edx(1);
+        if (!(features & (1 << X86_FEATURE_APIC))) {
+                pr_warning("Could not enable APIC!\n");
+                return -1;
+        }
+        set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+        mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
+
+        /* The BIOS may have set up the APIC at some other address */
+        rdmsr(MSR_IA32_APICBASE, l, h);
+        if (l & MSR_IA32_APICBASE_ENABLE)
+                mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+
+        pr_info("Found and enabled local APIC!\n");
+        return 0;
+}
+
+int apic_force_enable(void)
+{
+        u32 h, l;
+
+        if (disable_apic)
+                return -1;
+
+        /*
+         * Some BIOSes disable the local APIC in the APIC_BASE
+         * MSR. This can only be done in software for Intel P6 or later
+         * and AMD K7 (Model > 1) or later.
+         */
+        rdmsr(MSR_IA32_APICBASE, l, h);
+        if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+                pr_info("Local APIC disabled by BIOS -- reenabling.\n");
+                l &= ~MSR_IA32_APICBASE_BASE;
+                l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
+                wrmsr(MSR_IA32_APICBASE, l, h);
+                enabled_via_apicbase = 1;
+        }
+        return apic_verify();
+}
+
 /*
  * Detect and initialize APIC
  */
 static int __init detect_init_APIC(void)
 {
-        u32 h, l, features;
-
         /* Disabled by kernel option? */
         if (disable_apic)
                 return -1;
@@ -1574,38 +1614,12 @@ static int __init detect_init_APIC(void)
                                 "you can enable it with \"lapic\"\n");
                         return -1;
                 }
-                /*
-                 * Some BIOSes disable the local APIC in the APIC_BASE
-                 * MSR. This can only be done in software for Intel P6 or later
-                 * and AMD K7 (Model > 1) or later.
-                 */
-                rdmsr(MSR_IA32_APICBASE, l, h);
-                if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-                        pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-                        l &= ~MSR_IA32_APICBASE_BASE;
-                        l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
-                        wrmsr(MSR_IA32_APICBASE, l, h);
-                        enabled_via_apicbase = 1;
-                }
-        }
-        /*
-         * The APIC feature bit should now be enabled
-         * in `cpuid'
-         */
-        features = cpuid_edx(1);
-        if (!(features & (1 << X86_FEATURE_APIC))) {
-                pr_warning("Could not enable APIC!\n");
-                return -1;
+                if (apic_force_enable())
+                        return -1;
+        } else {
+                if (apic_verify())
+                        return -1;
         }
-        set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
-        mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-
-        /* The BIOS may have set up the APIC at some other address */
-        rdmsr(MSR_IA32_APICBASE, l, h);
-        if (l & MSR_IA32_APICBASE_ENABLE)
-                mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
-
-        pr_info("Found and enabled local APIC!\n");
 
         apic_pm_activate();
 
@@ -1617,28 +1631,6 @@ no_apic:
 }
 #endif
 
-#ifdef CONFIG_X86_64
-void __init early_init_lapic_mapping(void)
-{
-        /*
-         * If no local APIC can be found then go out
-         * : it means there is no mpatable and MADT
-         */
-        if (!smp_found_config)
-                return;
-
-        set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
-        apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
-                    APIC_BASE, mp_lapic_addr);
-
-        /*
-         * Fetch the APIC ID of the BSP in case we have a
-         * default configuration (or the MP table is broken).
-         */
-        boot_cpu_physical_apicid = read_apic_id();
-}
-#endif
-
 /**
  * init_apic_mappings - initialize APIC mappings
  */
@@ -1664,10 +1656,7 @@ void __init init_apic_mappings(void)
                  * acpi_register_lapic_address()
                  */
                 if (!acpi_lapic && !smp_found_config)
-                        set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-
-                apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
-                                        APIC_BASE, apic_phys);
+                        register_lapic_address(apic_phys);
         }
 
         /*
@@ -1689,11 +1678,27 @@ void __init init_apic_mappings(void)
         }
 }
 
+void __init register_lapic_address(unsigned long address)
+{
+        mp_lapic_addr = address;
+
+        if (!x2apic_mode) {
+                set_fixmap_nocache(FIX_APIC_BASE, address);
+                apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
+                            APIC_BASE, mp_lapic_addr);
+        }
+        if (boot_cpu_physical_apicid == -1U) {
+                boot_cpu_physical_apicid  = read_apic_id();
+                apic_version[boot_cpu_physical_apicid] =
+                         GET_APIC_VERSION(apic_read(APIC_LVR));
+        }
+}
+
 /*
  * This initializes the IO-APIC and APIC hardware if this is
  * a UP kernel.
  */
-int apic_version[MAX_APICS];
+int apic_version[MAX_LOCAL_APIC];
 
 int __init APIC_init_uniprocessor(void)
 {
@@ -1758,17 +1763,10 @@ int __init APIC_init_uniprocessor(void)
                 setup_IO_APIC();
         else {
                 nr_ioapics = 0;
-                localise_nmi_watchdog();
         }
-#else
-        localise_nmi_watchdog();
 #endif
 
         x86_init.timers.setup_percpu_clockev();
-#ifdef CONFIG_X86_64
-        check_nmi_watchdog();
-#endif
-
         return 0;
 }
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 62f6e1e55b90..79fd43ca6f96 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,20 +17,31 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(void)
 {
         return (u64)(cpu_khz) * 1000 * 60;
 }
+#endif
 
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
+#ifdef arch_trigger_all_cpu_backtrace
 /* For reliability, we're prepared to waste bits here. */
 static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
 
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
 void arch_trigger_all_cpu_backtrace(void)
 {
         int i;
 
+        if (test_and_set_bit(0, &backtrace_flag))
+                /*
+                 * If there is already a trigger_all_cpu_backtrace() in progress
+                 * (backtrace_flag == 1), don't output double cpu dump infos.
+                 */
+                return;
+
         cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
 
         printk(KERN_INFO "sending NMI to all CPUs:\n");
@@ -42,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void)
                         break;
                 mdelay(1);
         }
+
+        clear_bit(0, &backtrace_flag);
+        smp_mb__after_clear_bit();
 }
 
 static int __kprobes
@@ -50,11 +64,10 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 {
         struct die_args *args = __args;
         struct pt_regs *regs;
-        int cpu = smp_processor_id();
+        int cpu;
 
         switch (cmd) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 break;
 
         default:
@@ -62,6 +75,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
         }
 
         regs = args->regs;
+        cpu = smp_processor_id();
 
         if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
                 static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -81,7 +95,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block backtrace_notifier = {
         .notifier_call          = arch_trigger_all_cpu_backtrace_handler,
         .next                   = NULL,
-        .priority               = 1
+        .priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static int __init register_trigger_all_cpu_backtrace(void)
@@ -91,18 +105,3 @@ static int __init register_trigger_all_cpu_backtrace(void)
 }
 early_initcall(register_trigger_all_cpu_backtrace);
 #endif
-
-/* STUB calls to mimic old nmi_watchdog behaviour */
-#if defined(CONFIG_X86_LOCAL_APIC)
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-void acpi_nmi_enable(void) { return; }
-void acpi_nmi_disable(void) { return; }
-#endif
-atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-int unknown_nmi_panic;
-void cpu_nmi_set_wd_enabled(void) { return; }
-void stop_apic_nmi_watchdog(void *unused) { return; }
-void setup_apic_nmi_watchdog(void *unused) { return; }
-int __init check_nmi_watchdog(void) { return 0; }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fadcd743a74f..697dc34b7b87 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -54,7 +54,6 @@
 #include <asm/dma.h>
 #include <asm/timer.h>
 #include <asm/i8259.h>
-#include <asm/nmi.h>
 #include <asm/msidef.h>
 #include <asm/hypertransport.h>
 #include <asm/setup.h>
@@ -126,6 +125,26 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
+/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
+void mp_save_irq(struct mpc_intsrc *m)
+{
+        int i;
+
+        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
+                " IRQ %02x, APIC ID %x, APIC INT %02x\n",
+                m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbus,
+                m->srcbusirq, m->dstapic, m->dstirq);
+
+        for (i = 0; i < mp_irq_entries; i++) {
+                if (!memcmp(&mp_irqs[i], m, sizeof(*m)))
+                        return;
+        }
+
+        memcpy(&mp_irqs[mp_irq_entries], m, sizeof(*m));
+        if (++mp_irq_entries == MAX_IRQ_SOURCES)
+                panic("Max # of irq sources exceeded!!\n");
+}
+
 struct irq_pin_list {
         int apic, pin;
         struct irq_pin_list *next;
@@ -136,6 +155,7 @@ static struct irq_pin_list *alloc_irq_pin_list(int node)
         return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
+
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
 #ifdef CONFIG_SPARSE_IRQ
 static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY];
@@ -1934,8 +1954,7 @@ void disable_IO_APIC(void)
  *
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
-
-void __init setup_ioapic_ids_from_mpc(void)
+void __init setup_ioapic_ids_from_mpc_nocheck(void)
 {
         union IO_APIC_reg_00 reg_00;
         physid_mask_t phys_id_present_map;
@@ -1944,15 +1963,6 @@ void __init setup_ioapic_ids_from_mpc(void)
         unsigned char old_id;
         unsigned long flags;
 
-        if (acpi_ioapic)
-                return;
-        /*
-         * Don't check I/O APIC IDs for xAPIC systems.  They have
-         * no meaning without the serial APIC bus.
-         */
-        if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-                || APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-                return;
         /*
          * This is broken; anything with a real cpu count has to
          * circumvent this idiocy regardless.
@@ -2006,7 +2016,6 @@ void __init setup_ioapic_ids_from_mpc(void)
                         physids_or(phys_id_present_map, phys_id_present_map, tmp);
                 }
 
-
                 /*
                  * We need to adjust the IRQ routing table
                  * if the ID changed.
@@ -2018,9 +2027,12 @@ void __init setup_ioapic_ids_from_mpc(void)
                                                 = mp_ioapics[apic_id].apicid;
 
                 /*
-                 * Read the right value from the MPC table and
-                 * write it into the ID register.
+                 * Update the ID register according to the right value
+                 * from the MPC table if they are different.
                  */
+                if (mp_ioapics[apic_id].apicid == reg_00.bits.ID)
+                        continue;
+
                 apic_printk(APIC_VERBOSE, KERN_INFO
                         "...changing IO-APIC physical APIC ID to %d ...",
                         mp_ioapics[apic_id].apicid);
@@ -2042,6 +2054,21 @@ void __init setup_ioapic_ids_from_mpc(void)
                         apic_printk(APIC_VERBOSE, " ok.\n");
         }
 }
+
+void __init setup_ioapic_ids_from_mpc(void)
+{
+
+        if (acpi_ioapic)
+                return;
+        /*
+         * Don't check I/O APIC IDs for xAPIC systems.  They have
+         * no meaning without the serial APIC bus.
+         */
+        if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+                || APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+                return;
+        setup_ioapic_ids_from_mpc_nocheck();
+}
 #endif
 
 int no_timer_check __initdata;
@@ -2302,7 +2329,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
                 unsigned int irr;
                 struct irq_desc *desc;
                 struct irq_cfg *cfg;
-                irq = __get_cpu_var(vector_irq)[vector];
+                irq = __this_cpu_read(vector_irq[vector]);
 
                 if (irq == -1)
                         continue;
@@ -2336,7 +2363,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
                         apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
                         goto unlock;
                 }
-                __get_cpu_var(vector_irq)[vector] = -1;
+                __this_cpu_write(vector_irq[vector], -1);
 unlock:
                 raw_spin_unlock(&desc->lock);
         }
@@ -2642,24 +2669,6 @@ static void lapic_register_intr(int irq)
                                       "edge");
 }
 
-static void __init setup_nmi(void)
-{
-        /*
-         * Dirty trick to enable the NMI watchdog ...
-         * We put the 8259A master into AEOI mode and
-         * unmask on all local APICs LVT0 as NMI.
-         *
-         * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
-         * is from Maciej W. Rozycki - so we do not have to EOI from
-         * the NMI handler or the timer interrupt.
-         */
-        apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
-
-        enable_NMI_through_LVT0();
-
-        apic_printk(APIC_VERBOSE, " done.\n");
-}
-
 /*
  * This looks a bit hackish but it's about the only one way of sending
  * a few INTA cycles to 8259As and any associated glue logic.  ICR does
@@ -2765,15 +2774,6 @@ static inline void __init check_timer(void)
          */
         apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
         legacy_pic->init(1);
-#ifdef CONFIG_X86_32
-        {
-                unsigned int ver;
-
-                ver = apic_read(APIC_LVR);
-                ver = GET_APIC_VERSION(ver);
-                timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
-        }
-#endif
 
         pin1  = find_isa_irq_pin(0, mp_INT);
         apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2821,10 +2821,6 @@ static inline void __init check_timer(void)
                                 unmask_ioapic(cfg);
                 }
                 if (timer_irq_works()) {
-                        if (nmi_watchdog == NMI_IO_APIC) {
-                                setup_nmi();
-                                legacy_pic->unmask(0);
-                        }
                         if (disable_timer_pin_1 > 0)
                                 clear_IO_APIC_pin(0, pin1);
                         goto out;
@@ -2850,11 +2846,6 @@ static inline void __init check_timer(void)
                 if (timer_irq_works()) {
                         apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
                         timer_through_8259 = 1;
-                        if (nmi_watchdog == NMI_IO_APIC) {
-                                legacy_pic->mask(0);
-                                setup_nmi();
-                                legacy_pic->unmask(0);
-                        }
                         goto out;
                 }
                 /*
@@ -2866,15 +2857,6 @@ static inline void __init check_timer(void)
                 apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
         }
 
-        if (nmi_watchdog == NMI_IO_APIC) {
-                apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
-                            "through the IO-APIC - disabling NMI Watchdog!\n");
-                nmi_watchdog = NMI_NONE;
-        }
-#ifdef CONFIG_X86_32
-        timer_ack = 0;
-#endif
-
         apic_printk(APIC_QUIET, KERN_INFO
                     "...trying to set up timer as Virtual Wire IRQ...\n");
 
@@ -3639,7 +3621,7 @@ int __init io_apic_get_redir_entries (int ioapic)
         return reg_01.bits.entries + 1;
 }
 
-void __init probe_nr_irqs_gsi(void)
+static void __init probe_nr_irqs_gsi(void)
 {
         int nr;
 
@@ -3956,7 +3938,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
         return res;
 }
 
-void __init ioapic_init_mappings(void)
+void __init ioapic_and_gsi_init(void)
 {
         unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
         struct resource *ioapic_res;
@@ -3994,6 +3976,8 @@ fake_ioapic_page:
                 ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1;
                 ioapic_res++;
         }
+
+        probe_nr_irqs_gsi();
 }
 
 void __init ioapic_insert_resources(void)
@@ -4103,7 +4087,8 @@ void __init pre_init_apic_IRQ0(void)
 
         printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
-        phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+        physid_set_mask_of_physid(boot_cpu_physical_apicid,
+                                         &phys_cpu_present_map);
 #endif
         /* Make sure the irq descriptor is set up */
         cfg = alloc_irq_and_cfg_at(0, 0);
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
deleted file mode 100644
index c90041ccb742..000000000000
--- a/arch/x86/kernel/apic/nmi.c
+++ /dev/null
@@ -1,567 +0,0 @@
-/*
- *  NMI watchdog support on APIC systems
- *
- *  Started by Ingo Molnar <mingo@redhat.com>
- *
- *  Fixes:
- *  Mikael Pettersson   : AMD K7 support for local APIC NMI watchdog.
- *  Mikael Pettersson   : Power Management for local APIC NMI watchdog.
- *  Mikael Pettersson   : Pentium 4 support for local APIC NMI watchdog.
- *  Pavel Machek and
- *  Mikael Pettersson   : PM converted to driver model. Disable/enable API.
- */
-
-#include <asm/apic.h>
-
-#include <linux/nmi.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/sysdev.h>
-#include <linux/sysctl.h>
-#include <linux/percpu.h>
-#include <linux/kprobes.h>
-#include <linux/cpumask.h>
-#include <linux/kernel_stat.h>
-#include <linux/kdebug.h>
-#include <linux/smp.h>
-
-#include <asm/i8259.h>
-#include <asm/io_apic.h>
-#include <asm/proto.h>
-#include <asm/timer.h>
-
-#include <asm/mce.h>
-
-#include <asm/mach_traps.h>
-
-int unknown_nmi_panic;
-int nmi_watchdog_enabled;
-
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
-/* nmi_active:
- * >0: the lapic NMI watchdog is active, but can be disabled
- * <0: the lapic NMI watchdog has not been set up, and cannot
- *     be enabled
- *  0: the lapic NMI watchdog is disabled, but can be enabled
- */
-atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-
-static int panic_on_timeout;
-
-static unsigned int nmi_hz = HZ;
-static DEFINE_PER_CPU(short, wd_enabled);
-static int endflag __initdata;
-
-static inline unsigned int get_nmi_count(int cpu)
-{
-        return per_cpu(irq_stat, cpu).__nmi_count;
-}
-
-static inline int mce_in_progress(void)
-{
-#if defined(CONFIG_X86_MCE)
-        return atomic_read(&mce_entry) > 0;
-#endif
-        return 0;
-}
-
-/*
- * Take the local apic timer and PIT/HPET into account. We don't
- * know which one is active, when we have highres/dyntick on
- */
-static inline unsigned int get_timer_irqs(int cpu)
-{
-        return per_cpu(irq_stat, cpu).apic_timer_irqs +
-                per_cpu(irq_stat, cpu).irq0_irqs;
-}
-
-#ifdef CONFIG_SMP
-/*
- * The performance counters used by NMI_LOCAL_APIC don't trigger when
- * the CPU is idle. To make sure the NMI watchdog really ticks on all
- * CPUs during the test make them busy.
- */
-static __init void nmi_cpu_busy(void *data)
-{
-        local_irq_enable_in_hardirq();
-        /*
-         * Intentionally don't use cpu_relax here. This is
-         * to make sure that the performance counter really ticks,
-         * even if there is a simulator or similar that catches the
-         * pause instruction. On a real HT machine this is fine because
-         * all other CPUs are busy with "useless" delay loops and don't
-         * care if they get somewhat less cycles.
-         */
-        while (endflag == 0)
-                mb();
-}
-#endif
-
-static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
-{
-        printk(KERN_CONT "\n");
-
-        printk(KERN_WARNING
-                "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
-                        cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
-
-        printk(KERN_WARNING
-                "Please report this to bugzilla.kernel.org,\n");
-        printk(KERN_WARNING
-                "and attach the output of the 'dmesg' command.\n");
-
-        per_cpu(wd_enabled, cpu) = 0;
-        atomic_dec(&nmi_active);
-}
-
-static void __acpi_nmi_disable(void *__unused)
-{
-        apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
-
-int __init check_nmi_watchdog(void)
-{
-        unsigned int *prev_nmi_count;
-        int cpu;
-
-        if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
-                return 0;
-
-        prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
-        if (!prev_nmi_count)
-                goto error;
-
-        printk(KERN_INFO "Testing NMI watchdog ... ");
-
-#ifdef CONFIG_SMP
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
-#endif
-
-        for_each_possible_cpu(cpu)
-                prev_nmi_count[cpu] = get_nmi_count(cpu);
-        local_irq_enable();
-        mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
-
-        for_each_online_cpu(cpu) {
-                if (!per_cpu(wd_enabled, cpu))
-                        continue;
-                if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
-                        report_broken_nmi(cpu, prev_nmi_count);
-        }
-        endflag = 1;
-        if (!atomic_read(&nmi_active)) {
-                kfree(prev_nmi_count);
-                atomic_set(&nmi_active, -1);
-                goto error;
-        }
-        printk("OK.\n");
-
-        /*
-         * now that we know it works we can reduce NMI frequency to
-         * something more reasonable; makes a difference in some configs
-         */
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                nmi_hz = lapic_adjust_nmi_hz(1);
-
-        kfree(prev_nmi_count);
-        return 0;
-error:
-        if (nmi_watchdog == NMI_IO_APIC) {
-                if (!timer_through_8259)
-                        legacy_pic->mask(0);
-                on_each_cpu(__acpi_nmi_disable, NULL, 1);
-        }
-
-#ifdef CONFIG_X86_32
-        timer_ack = 0;
-#endif
-        return -1;
-}
-
-static int __init setup_nmi_watchdog(char *str)
-{
-        unsigned int nmi;
-
-        if (!strncmp(str, "panic", 5)) {
-                panic_on_timeout = 1;
-                str = strchr(str, ',');
-                if (!str)
-                        return 1;
-                ++str;
-        }
-
-        if (!strncmp(str, "lapic", 5))
-                nmi_watchdog = NMI_LOCAL_APIC;
-        else if (!strncmp(str, "ioapic", 6))
-                nmi_watchdog = NMI_IO_APIC;
-        else {
-                get_option(&str, &nmi);
-                if (nmi >= NMI_INVALID)
-                        return 0;
-                nmi_watchdog = nmi;
-        }
-
-        return 1;
-}
-__setup("nmi_watchdog=", setup_nmi_watchdog);
-
-/*
- * Suspend/resume support
- */
-#ifdef CONFIG_PM
-
-static int nmi_pm_active; /* nmi_active before suspend */
-
-static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
-{
-        /* only CPU0 goes here, other CPUs should be offline */
-        nmi_pm_active = atomic_read(&nmi_active);
-        stop_apic_nmi_watchdog(NULL);
-        BUG_ON(atomic_read(&nmi_active) != 0);
-        return 0;
-}
-
-static int lapic_nmi_resume(struct sys_device *dev)
-{
-        /* only CPU0 goes here, other CPUs should be offline */
-        if (nmi_pm_active > 0) {
-                setup_apic_nmi_watchdog(NULL);
-                touch_nmi_watchdog();
-        }
-        return 0;
-}
-
-static struct sysdev_class nmi_sysclass = {
-        .name           = "lapic_nmi",
-        .resume         = lapic_nmi_resume,
-        .suspend        = lapic_nmi_suspend,
-};
-
-static struct sys_device device_lapic_nmi = {
-        .id     = 0,
-        .cls    = &nmi_sysclass,
-};
-
-static int __init init_lapic_nmi_sysfs(void)
-{
-        int error;
-
-        /*
-         * should really be a BUG_ON but b/c this is an
-         * init call, it just doesn't work.  -dcz
-         */
-        if (nmi_watchdog != NMI_LOCAL_APIC)
-                return 0;
-
-        if (atomic_read(&nmi_active) < 0)
-                return 0;
-
-        error = sysdev_class_register(&nmi_sysclass);
-        if (!error)
-                error = sysdev_register(&device_lapic_nmi);
-        return error;
-}
-
-/* must come after the local APIC's device_initcall() */
-late_initcall(init_lapic_nmi_sysfs);
-
-#endif  /* CONFIG_PM */
-
-static void __acpi_nmi_enable(void *__unused)
-{
-        apic_write(APIC_LVT0, APIC_DM_NMI);
-}
-
-/*
- * Enable timer based NMIs on all CPUs:
- */
-void acpi_nmi_enable(void)
-{
-        if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-                on_each_cpu(__acpi_nmi_enable, NULL, 1);
-}
-
-/*
- * Disable timer based NMIs on all CPUs:
- */
-void acpi_nmi_disable(void)
-{
-        if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-                on_each_cpu(__acpi_nmi_disable, NULL, 1);
-}
-
-/*
- * This function is called as soon the LAPIC NMI watchdog driver has everything
- * in place and it's ready to check if the NMIs belong to the NMI watchdog
- */
-void cpu_nmi_set_wd_enabled(void)
-{
-        __get_cpu_var(wd_enabled) = 1;
-}
-
-void setup_apic_nmi_watchdog(void *unused)
-{
-        if (__get_cpu_var(wd_enabled))
-                return;
-
-        /* cheap hack to support suspend/resume */
-        /* if cpu0 is not active neither should the other cpus */
-        if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
-                return;
-
-        switch (nmi_watchdog) {
-        case NMI_LOCAL_APIC:
-                if (lapic_watchdog_init(nmi_hz) < 0) {
-                        __get_cpu_var(wd_enabled) = 0;
-                        return;
-                }
-                /* FALL THROUGH */
-        case NMI_IO_APIC:
-                __get_cpu_var(wd_enabled) = 1;
-                atomic_inc(&nmi_active);
-        }
-}
-
-void stop_apic_nmi_watchdog(void *unused)
-{
-        /* only support LOCAL and IO APICs for now */
-        if (!nmi_watchdog_active())
-                return;
-        if (__get_cpu_var(wd_enabled) == 0)
-                return;
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                lapic_watchdog_stop();
-        else
-                __acpi_nmi_disable(NULL);
-        __get_cpu_var(wd_enabled) = 0;
-        atomic_dec(&nmi_active);
-}
-
-/*
- * the best way to detect whether a CPU has a 'hard lockup' problem
- * is to check it's local APIC timer IRQ counts. If they are not
- * changing then that CPU has some problem.
- *
- * as these watchdog NMI IRQs are generated on every CPU, we only
- * have to check the current processor.
- *
- * since NMIs don't listen to _any_ locks, we have to be extremely
- * careful not to rely on unsafe variables. The printk might lock
- * up though, so we have to break up any console locks first ...
- * [when there will be more tty-related locks, break them up here too!]
- */
-
-static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(long, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
-
-void touch_nmi_watchdog(void)
-{
-        if (nmi_watchdog_active()) {
-                unsigned cpu;
-
-                /*
-                 * Tell other CPUs to reset their alert counters. We cannot
-                 * do it ourselves because the alert count increase is not
-                 * atomic.
-                 */
-                for_each_present_cpu(cpu) {
-                        if (per_cpu(nmi_touch, cpu) != 1)
-                                per_cpu(nmi_touch, cpu) = 1;
-                }
-        }
-
-        /*
-         * Tickle the softlockup detector too:
-         */
-        touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-notrace __kprobes int
-nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
-{
-        /*
-         * Since current_thread_info()-> is always on the stack, and we
-         * always switch the stack NMI-atomically, it's safe to use
-         * smp_processor_id().
-         */
-        unsigned int sum;
-        int touched = 0;
-        int cpu = smp_processor_id();
-        int rc = 0;
-
-        sum = get_timer_irqs(cpu);
-
-        if (__get_cpu_var(nmi_touch)) {
-                __get_cpu_var(nmi_touch) = 0;
-                touched = 1;
-        }
-
-        /* We can be called before check_nmi_watchdog, hence NULL check. */
-        if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-                static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */
-
-                raw_spin_lock(&lock);
-                printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
-                show_regs(regs);
-                dump_stack();
-                raw_spin_unlock(&lock);
-                cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
-
-                rc = 1;
-        }
-
-        /* Could check oops_in_progress here too, but it's safer not to */
-        if (mce_in_progress())
-                touched = 1;
-
-        /* if the none of the timers isn't firing, this cpu isn't doing much */
-        if (!touched && __get_cpu_var(last_irq_sum) == sum) {
-                /*
-                 * Ayiee, looks like this CPU is stuck ...
-                 * wait a few IRQs (5 seconds) before doing the oops ...
-                 */
-                __this_cpu_inc(alert_counter);
-                if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
-                        /*
-                         * die_nmi will return ONLY if NOTIFY_STOP happens..
-                         */
-                        die_nmi("BUG: NMI Watchdog detected LOCKUP",
-                                regs, panic_on_timeout);
-        } else {
-                __get_cpu_var(last_irq_sum) = sum;
-                __this_cpu_write(alert_counter, 0);
-        }
-
-        /* see if the nmi watchdog went off */
-        if (!__get_cpu_var(wd_enabled))
-                return rc;
-        switch (nmi_watchdog) {
-        case NMI_LOCAL_APIC:
-                rc |= lapic_wd_event(nmi_hz);
-                break;
-        case NMI_IO_APIC:
-                /*
-                 * don't know how to accurately check for this.
-                 * just assume it was a watchdog timer interrupt
-                 * This matches the old behaviour.
-                 */
-                rc = 1;
-                break;
-        }
-        return rc;
-}
-
-#ifdef CONFIG_SYSCTL
-
-static void enable_ioapic_nmi_watchdog_single(void *unused)
-{
-        __get_cpu_var(wd_enabled) = 1;
-        atomic_inc(&nmi_active);
-        __acpi_nmi_enable(NULL);
-}
-
-static void enable_ioapic_nmi_watchdog(void)
-{
-        on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
-        touch_nmi_watchdog();
-}
-
-static void disable_ioapic_nmi_watchdog(void)
-{
-        on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-}
-
-static int __init setup_unknown_nmi_panic(char *str)
-{
-        unknown_nmi_panic = 1;
-        return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
-{
-        unsigned char reason = get_nmi_reason();
-        char buf[64];
-
-        sprintf(buf, "NMI received for unknown reason %02x\n", reason);
-        die_nmi(buf, regs, 1); /* Always panic here */
-        return 0;
-}
-
-/*
- * proc handler for /proc/sys/kernel/nmi
- */
-int proc_nmi_enabled(struct ctl_table *table, int write,
-                        void __user *buffer, size_t *length, loff_t *ppos)
-{
-        int old_state;
-
-        nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
-        old_state = nmi_watchdog_enabled;
-        proc_dointvec(table, write, buffer, length, ppos);
-        if (!!old_state == !!nmi_watchdog_enabled)
-                return 0;
-
-        if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
-                printk(KERN_WARNING
-                        "NMI watchdog is permanently disabled\n");
-                return -EIO;
-        }
-
-        if (nmi_watchdog == NMI_LOCAL_APIC) {
-                if (nmi_watchdog_enabled)
-                        enable_lapic_nmi_watchdog();
-                else
-                        disable_lapic_nmi_watchdog();
-        } else if (nmi_watchdog == NMI_IO_APIC) {
-                if (nmi_watchdog_enabled)
-                        enable_ioapic_nmi_watchdog();
-                else
-                        disable_ioapic_nmi_watchdog();
-        } else {
-                printk(KERN_WARNING
-                        "NMI watchdog doesn't know what hardware to touch\n");
-                return -EIO;
-        }
-        return 0;
-}
-
-#endif /* CONFIG_SYSCTL */
-
-int do_nmi_callback(struct pt_regs *regs, int cpu)
-{
-#ifdef CONFIG_SYSCTL
-        if (unknown_nmi_panic)
-                return unknown_nmi_panic_callback(regs, cpu);
-#endif
-        return 0;
-}
-
-void arch_trigger_all_cpu_backtrace(void)
-{
-        int i;
-
-        cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
-
-        printk(KERN_INFO "sending NMI to all CPUs:\n");
-        apic->send_IPI_all(NMI_VECTOR);
-
-        /* Wait for up to 10 seconds for all CPUs to do the backtrace */
-        for (i = 0; i < 10 * 1000; i++) {
-                if (cpumask_empty(to_cpumask(backtrace_mask)))
-                        break;
-                mdelay(1);
-        }
-}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index c1c52c341f40..bd16b58b8850 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -48,6 +48,16 @@ unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 static DEFINE_SPINLOCK(uv_nmi_lock);
 
+static unsigned long __init uv_early_read_mmr(unsigned long addr)
+{
+        unsigned long val, *mmr;
+
+        mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
+        val = *mmr;
+        early_iounmap(mmr, sizeof(*mmr));
+        return val;
+}
+
 static inline bool is_GRU_range(u64 start, u64 end)
 {
         return start >= gru_start_paddr && end <= gru_end_paddr;
@@ -58,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end)
         return is_ISA_range(start, end) || is_GRU_range(start, end);
 }
 
-static int early_get_nodeid(void)
+static int __init early_get_pnodeid(void)
 {
         union uvh_node_id_u node_id;
-        unsigned long *mmr;
-
-        mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
-        node_id.v = *mmr;
-        early_iounmap(mmr, sizeof(*mmr));
+        union uvh_rh_gam_config_mmr_u  m_n_config;
+        int pnode;
 
         /* Currently, all blades have same revision number */
+        node_id.v = uv_early_read_mmr(UVH_NODE_ID);
+        m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
         uv_min_hub_revision_id = node_id.s.revision;
 
-        return node_id.s.node_id;
+        pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+        return pnode;
 }
 
 static void __init early_get_apic_pnode_shift(void)
 {
-        unsigned long *mmr;
-
-        mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr));
-        uvh_apicid.v = *mmr;
-        early_iounmap(mmr, sizeof(*mmr));
+        uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
         if (!uvh_apicid.v)
                 /*
                  * Old bios, use default value
@@ -95,21 +101,17 @@ static void __init early_get_apic_pnode_shift(void)
 static void __init uv_set_apicid_hibit(void)
 {
         union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
-        unsigned long *mmr;
 
-        mmr = early_ioremap(UV_LOCAL_MMR_BASE |
-                UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK, sizeof(*mmr));
-        apicid_mask.v = *mmr;
-        early_iounmap(mmr, sizeof(*mmr));
+        apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
         uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-        int nodeid;
+        int pnodeid;
 
         if (!strcmp(oem_id, "SGI")) {
-                nodeid = early_get_nodeid();
+                pnodeid = early_get_pnodeid();
                 early_get_apic_pnode_shift();
                 x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
                 x86_platform.nmi_init = uv_nmi_init;
@@ -118,8 +120,8 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                 else if (!strcmp(oem_table_id, "UVX"))
                         uv_system_type = UV_X2APIC;
                 else if (!strcmp(oem_table_id, "UVH")) {
-                        __get_cpu_var(x2apic_extra_bits) =
-                                nodeid << (uvh_apicid.s.pnode_shift - 1);
+                        __this_cpu_write(x2apic_extra_bits,
+                                pnodeid << uvh_apicid.s.pnode_shift);
                         uv_system_type = UV_NON_UNIQUE_APIC;
                         uv_set_apicid_hibit();
                         return 1;
@@ -284,7 +286,7 @@ static unsigned int x2apic_get_apic_id(unsigned long x)
         unsigned int id;
 
         WARN_ON(preemptible() && num_online_cpus() > 1);
-        id = x | __get_cpu_var(x2apic_extra_bits);
+        id = x | __this_cpu_read(x2apic_extra_bits);
 
         return id;
 }
@@ -376,7 +378,7 @@ struct apic __refdata apic_x2apic_uv_x = {
 
 static __cpuinit void set_x2apic_extra_bits(int pnode)
 {
-        __get_cpu_var(x2apic_extra_bits) = (pnode << 6);
+        __this_cpu_write(x2apic_extra_bits, pnode << uvh_apicid.s.pnode_shift);
 }
 
 /*
@@ -639,7 +641,7 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
-        if (reason != DIE_NMI_IPI)
+        if (reason != DIE_NMIUNKNOWN)
                 return NOTIFY_OK;
 
         if (in_crash_kexec)
@@ -682,27 +684,32 @@ void uv_nmi_init(void)
 void __init uv_system_init(void)
 {
         union uvh_rh_gam_config_mmr_u  m_n_config;
+        union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
         union uvh_node_id_u node_id;
         unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
-        int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+        int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io;
         int gnode_extra, max_pnode = 0;
         unsigned long mmr_base, present, paddr;
-        unsigned short pnode_mask;
+        unsigned short pnode_mask, pnode_io_mask;
 
         map_low_mmrs();
 
         m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
         m_val = m_n_config.s.m_skt;
         n_val = m_n_config.s.n_skt;
+        mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+        n_io = mmioh.s.n_io;
         mmr_base =
             uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
             ~UV_MMR_ENABLE;
         pnode_mask = (1 << n_val) - 1;
+        pnode_io_mask = (1 << n_io) - 1;
+
         node_id.v = uv_read_local_mmr(UVH_NODE_ID);
         gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
         gnode_upper = ((unsigned long)gnode_extra  << m_val);
-        printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
-                        n_val, m_val, gnode_upper, gnode_extra);
+        printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n",
+                        n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask);
 
         printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
@@ -735,7 +742,7 @@ void __init uv_system_init(void)
                 for (j = 0; j < 64; j++) {
                         if (!test_bit(j, &present))
                                 continue;
-                        pnode = (i * 64 + j);
+                        pnode = (i * 64 + j) & pnode_mask;
                         uv_blade_info[blade].pnode = pnode;
                         uv_blade_info[blade].nr_possible_cpus = 0;
                         uv_blade_info[blade].nr_online_cpus = 0;
@@ -756,6 +763,7 @@ void __init uv_system_init(void)
                 /*
                  * apic_pnode_shift must be set before calling uv_apicid_to_pnode();
                  */
+                uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
                 uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
                 pnode = uv_apicid_to_pnode(apicid);
                 blade = boot_pnode_to_blade(pnode);
@@ -772,7 +780,6 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->numa_blade_id = blade;
                 uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
                 uv_cpu_hub_info(cpu)->pnode = pnode;
-                uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
                 uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
                 uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
                 uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
@@ -796,7 +803,7 @@ void __init uv_system_init(void)
 
         map_gru_high(max_pnode);
         map_mmr_high(max_pnode);
-        map_mmioh_high(max_pnode);
+        map_mmioh_high(max_pnode & pnode_io_mask);
 
         uv_cpu_init();
         uv_scir_register_cpu_notifier();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9e093f8fe78c..7c7bedb83c5a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -668,7 +668,7 @@ EXPORT_SYMBOL_GPL(amd_erratum_383);
 
 bool cpu_has_amd_erratum(const int *erratum)
 {
-        struct cpuinfo_x86 *cpu = &current_cpu_data;
+        struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
         int osvw_id = *erratum++;
         u32 range;
         u32 ms;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4b68bda30938..1d59834396bd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -894,7 +894,6 @@ void __init identify_boot_cpu(void)
 #else
         vgetcpu_set_mode();
 #endif
-        init_hw_perf_events();
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 491977baf6c0..35c7e65e59be 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -521,7 +521,7 @@ static void check_supported_cpu(void *_rc)
 
         *rc = -ENODEV;
 
-        if (current_cpu_data.x86_vendor != X86_VENDOR_AMD)
+        if (__this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_AMD)
                 return;
 
         eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
@@ -1377,7 +1377,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
 static void query_values_on_cpu(void *_err)
 {
         int *err = _err;
-        struct powernow_k8_data *data = __get_cpu_var(powernow_data);
+        struct powernow_k8_data *data = __this_cpu_read(powernow_data);
 
         *err = query_current_values_with_pending_wait(data);
 }
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 17ad03366211..7283e98deaae 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -149,8 +149,7 @@ union _cpuid4_leaf_ecx {
 };
 
 struct amd_l3_cache {
-        struct   pci_dev *dev;
-        bool     can_disable;
+        struct   amd_northbridge *nb;
         unsigned indices;
         u8       subcaches[4];
 };
@@ -266,7 +265,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
                 line_size = l2.line_size;
                 lines_per_tag = l2.lines_per_tag;
                 /* cpu_data has errata corrections for K7 applied */
-                size_in_kb = current_cpu_data.x86_cache_size;
+                size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
                 break;
         case 3:
                 if (!l3.val)
@@ -288,7 +287,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
         eax->split.type = types[leaf];
         eax->split.level = levels[leaf];
         eax->split.num_threads_sharing = 0;
-        eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+        eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1;
 
 
         if (assoc == 0xffff)
@@ -311,14 +310,12 @@ struct _cache_attr {
 /*
  * L3 cache descriptors
  */
-static struct amd_l3_cache **__cpuinitdata l3_caches;
-
 static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 {
         unsigned int sc0, sc1, sc2, sc3;
         u32 val = 0;
 
-        pci_read_config_dword(l3->dev, 0x1C4, &val);
+        pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
 
         /* calculate subcache sizes */
         l3->subcaches[0] = sc0 = !(val & BIT(0));
@@ -330,47 +327,14 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
         l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
-{
-        struct amd_l3_cache *l3;
-        struct pci_dev *dev = node_to_k8_nb_misc(node);
-
-        l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
-        if (!l3) {
-                printk(KERN_WARNING "Error allocating L3 struct\n");
-                return NULL;
-        }
-
-        l3->dev = dev;
-
-        amd_calc_l3_indices(l3);
-
-        return l3;
-}
-
-static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
-                                           int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
+                                        int index)
 {
+        static struct amd_l3_cache *__cpuinitdata l3_caches;
         int node;
 
-        if (boot_cpu_data.x86 != 0x10)
-                return;
-
-        if (index < 3)
-                return;
-
-        /* see errata #382 and #388 */
-        if (boot_cpu_data.x86_model < 0x8)
-                return;
-
-        if ((boot_cpu_data.x86_model == 0x8 ||
-             boot_cpu_data.x86_model == 0x9)
-                &&
-             boot_cpu_data.x86_mask < 0x1)
-                        return;
-
-        /* not in virtualized environments */
-        if (k8_northbridges.num == 0)
+        /* only for L3, and not in virtualized environments */
+        if (index < 3 || amd_nb_num() == 0)
                 return;
 
         /*
@@ -378,7 +342,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
          * never freed but this is done only on shutdown so it doesn't matter.
          */
         if (!l3_caches) {
-                int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
+                int size = amd_nb_num() * sizeof(struct amd_l3_cache);
 
                 l3_caches = kzalloc(size, GFP_ATOMIC);
                 if (!l3_caches)
@@ -387,14 +351,12 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 
         node = amd_get_nb_id(smp_processor_id());
 
-        if (!l3_caches[node]) {
-                l3_caches[node] = amd_init_l3_cache(node);
-                l3_caches[node]->can_disable = true;
+        if (!l3_caches[node].nb) {
+                l3_caches[node].nb = node_to_amd_nb(node);
+                amd_calc_l3_indices(&l3_caches[node]);
         }
 
-        WARN_ON(!l3_caches[node]);
-
-        this_leaf->l3 = l3_caches[node];
+        this_leaf->l3 = &l3_caches[node];
 }
 
 /*
@@ -408,7 +370,7 @@ int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
 {
         unsigned int reg = 0;
 
-        pci_read_config_dword(l3->dev, 0x1BC + slot * 4, &reg);
+        pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, &reg);
 
         /* check whether this slot is activated already */
         if (reg & (3UL << 30))
@@ -422,7 +384,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
 {
         int index;
 
-        if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+        if (!this_leaf->l3 ||
+            !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
                 return -EINVAL;
 
         index = amd_get_l3_disable_slot(this_leaf->l3, slot);
@@ -457,7 +420,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
                 if (!l3->subcaches[i])
                         continue;
 
-                pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+                pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 
                 /*
                  * We need to WBINVD on a core on the node containing the L3
@@ -467,7 +430,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
                 wbinvd_on_cpu(cpu);
 
                 reg |= BIT(31);
-                pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+                pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
         }
 }
 
@@ -524,7 +487,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
-        if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+        if (!this_leaf->l3 ||
+            !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
                 return -EINVAL;
 
         cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
@@ -545,7 +509,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 #define STORE_CACHE_DISABLE(slot)                                       \
 static ssize_t                                                          \
 store_cache_disable_##slot(struct _cpuid4_info *this_leaf,              \
-                            const char *buf, size_t count)              \
+                           const char *buf, size_t count)               \
 {                                                                       \
         return store_cache_disable(this_leaf, buf, count, slot);        \
 }
@@ -558,10 +522,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
                 show_cache_disable_1, store_cache_disable_1);
 
 #else   /* CONFIG_AMD_NB */
-static void __cpuinit
-amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
-{
-};
+#define amd_init_l3_cache(x, y)
 #endif /* CONFIG_AMD_NB */
 
 static int
@@ -575,7 +536,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 
         if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
                 amd_cpuid4(index, &eax, &ebx, &ecx);
-                amd_check_l3_disable(this_leaf, index);
+                amd_init_l3_cache(this_leaf, index);
         } else {
                 cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
         }
@@ -983,30 +944,48 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-#define DEFAULT_SYSFS_CACHE_ATTRS       \
-        &type.attr,                     \
-        &level.attr,                    \
-        &coherency_line_size.attr,      \
-        &physical_line_partition.attr,  \
-        &ways_of_associativity.attr,    \
-        &number_of_sets.attr,           \
-        &size.attr,                     \
-        &shared_cpu_map.attr,           \
-        &shared_cpu_list.attr
-
 static struct attribute *default_attrs[] = {
-        DEFAULT_SYSFS_CACHE_ATTRS,
+        &type.attr,
+        &level.attr,
+        &coherency_line_size.attr,
+        &physical_line_partition.attr,
+        &ways_of_associativity.attr,
+        &number_of_sets.attr,
+        &size.attr,
+        &shared_cpu_map.attr,
+        &shared_cpu_list.attr,
         NULL
 };
 
-static struct attribute *default_l3_attrs[] = {
-        DEFAULT_SYSFS_CACHE_ATTRS,
 #ifdef CONFIG_AMD_NB
-        &cache_disable_0.attr,
-        &cache_disable_1.attr,
+static struct attribute ** __cpuinit amd_l3_attrs(void)
+{
+        static struct attribute **attrs;
+        int n;
+
+        if (attrs)
+                return attrs;
+
+        n = sizeof (default_attrs) / sizeof (struct attribute *);
+
+        if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+                n += 2;
+
+        attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
+        if (attrs == NULL)
+                return attrs = default_attrs;
+
+        for (n = 0; default_attrs[n]; n++)
+                attrs[n] = default_attrs[n];
+
+        if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+                attrs[n++] = &cache_disable_0.attr;
+                attrs[n++] = &cache_disable_1.attr;
+        }
+
+        return attrs;
+}
 #endif
-        NULL
-};
 
 static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 {
@@ -1117,11 +1096,11 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
                 this_leaf = CPUID4_INFO_IDX(cpu, i);
 
-                if (this_leaf->l3 && this_leaf->l3->can_disable)
-                        ktype_cache.default_attrs = default_l3_attrs;
-                else
-                        ktype_cache.default_attrs = default_attrs;
-
+                ktype_cache.default_attrs = default_attrs;
+#ifdef CONFIG_AMD_NB
+                if (this_leaf->l3)
+                        ktype_cache.default_attrs = amd_l3_attrs();
+#endif
                 retval = kobject_init_and_add(&(this_object->kobj),
                                               &ktype_cache,
                                               per_cpu(ici_cache_kobject, cpu),
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7bfedb..a77971979564 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
         struct die_args *args = (struct die_args *)data;
         int cpu = smp_processor_id();
         struct mce *m = &__get_cpu_var(injectm);
-        if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+        if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
                 return NOTIFY_DONE;
         cpumask_clear_cpu(cpu, mce_inject_cpumask);
         if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
         .notifier_call = mce_raise_notify,
-        .priority = 1000,
+        .priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a35b72d7c03..d916183b7f9c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -326,7 +326,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 
 static int msr_to_offset(u32 msr)
 {
-        unsigned bank = __get_cpu_var(injectm.bank);
+        unsigned bank = __this_cpu_read(injectm.bank);
 
         if (msr == rip_msr)
                 return offsetof(struct mce, ip);
@@ -346,7 +346,7 @@ static u64 mce_rdmsrl(u32 msr)
 {
         u64 v;
 
-        if (__get_cpu_var(injectm).finished) {
+        if (__this_cpu_read(injectm.finished)) {
                 int offset = msr_to_offset(msr);
 
                 if (offset < 0)
@@ -369,7 +369,7 @@ static u64 mce_rdmsrl(u32 msr)
 
 static void mce_wrmsrl(u32 msr, u64 v)
 {
-        if (__get_cpu_var(injectm).finished) {
+        if (__this_cpu_read(injectm.finished)) {
                 int offset = msr_to_offset(msr);
 
                 if (offset >= 0)
@@ -1159,7 +1159,7 @@ static void mce_start_timer(unsigned long data)
 
         WARN_ON(smp_processor_id() != data);
 
-        if (mce_available(&current_cpu_data)) {
+        if (mce_available(__this_cpu_ptr(&cpu_info))) {
                 machine_check_poll(MCP_TIMESTAMP,
                                 &__get_cpu_var(mce_poll_banks));
         }
@@ -1767,7 +1767,7 @@ static int mce_shutdown(struct sys_device *dev)
 static int mce_resume(struct sys_device *dev)
 {
         __mcheck_cpu_init_generic();
-        __mcheck_cpu_init_vendor(&current_cpu_data);
+        __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
 
         return 0;
 }
@@ -1775,7 +1775,7 @@ static int mce_resume(struct sys_device *dev)
 static void mce_cpu_restart(void *data)
 {
         del_timer_sync(&__get_cpu_var(mce_timer));
-        if (!mce_available(&current_cpu_data))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)))
                 return;
         __mcheck_cpu_init_generic();
         __mcheck_cpu_init_timer();
@@ -1790,7 +1790,7 @@ static void mce_restart(void)
 /* Toggle features for corrected errors */
 static void mce_disable_ce(void *all)
 {
-        if (!mce_available(&current_cpu_data))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)))
                 return;
         if (all)
                 del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1799,7 +1799,7 @@ static void mce_disable_ce(void *all)
 
 static void mce_enable_ce(void *all)
 {
-        if (!mce_available(&current_cpu_data))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)))
                 return;
         cmci_reenable();
         cmci_recheck();
@@ -2022,7 +2022,7 @@ static void __cpuinit mce_disable_cpu(void *h)
         unsigned long action = *(unsigned long *)h;
         int i;
 
-        if (!mce_available(&current_cpu_data))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)))
                 return;
 
         if (!(action & CPU_TASKS_FROZEN))
@@ -2040,7 +2040,7 @@ static void __cpuinit mce_reenable_cpu(void *h)
         unsigned long action = *(unsigned long *)h;
         int i;
 
-        if (!mce_available(&current_cpu_data))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)))
                 return;
 
         if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 80c482382d5c..5bf2fac52aca 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -31,8 +31,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
-#define PFX               "mce_threshold: "
-#define VERSION           "version 1.1.1"
 #define NR_BANKS          6
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -59,12 +57,6 @@ struct threshold_block {
         struct list_head        miscj;
 };
 
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
-        .interrupt_enable       = 0,
-        .threshold_limit        = THRESHOLD_MAX,
-};
-
 struct threshold_bank {
         struct kobject          *kobj;
         struct threshold_block  *blocks;
@@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void);
 struct thresh_restart {
         struct threshold_block  *b;
         int                     reset;
+        int                     set_lvt_off;
+        int                     lvt_off;
         u16                     old_limit;
 };
 
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+        int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+        if (apic < 0) {
+                pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+                       "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+                       b->bank, b->block, b->address, hi, lo);
+                return 0;
+        }
+
+        if (apic != msr) {
+                pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+                       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+                       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+                return 0;
+        }
+
+        return 1;
+};
+
 /* must be called with correct cpu affinity */
 /* Called via smp_call_function_single() */
 static void threshold_restart_bank(void *_tr)
 {
         struct thresh_restart *tr = _tr;
-        u32 mci_misc_hi, mci_misc_lo;
+        u32 hi, lo;
 
-        rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+        rdmsr(tr->b->address, lo, hi);
 
-        if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+        if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
                 tr->reset = 1;  /* limit cannot be lower than err count */
 
         if (tr->reset) {                /* reset err count and overflow bit */
-                mci_misc_hi =
-                    (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+                hi =
+                    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
                     (THRESHOLD_MAX - tr->b->threshold_limit);
         } else if (tr->old_limit) {     /* change limit w/o reset */
-                int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+                int new_count = (hi & THRESHOLD_MAX) +
                     (tr->old_limit - tr->b->threshold_limit);
 
-                mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+                hi = (hi & ~MASK_ERR_COUNT_HI) |
                     (new_count & THRESHOLD_MAX);
         }
 
+        if (tr->set_lvt_off) {
+                if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+                        /* set new lvt offset */
+                        hi &= ~MASK_LVTOFF_HI;
+                        hi |= tr->lvt_off << 20;
+                }
+        }
+
         tr->b->interrupt_enable ?
-            (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
-            (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+            (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+            (hi &= ~MASK_INT_TYPE_HI);
 
-        mci_misc_hi |= MASK_COUNT_EN_HI;
-        wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+        hi |= MASK_COUNT_EN_HI;
+        wrmsr(tr->b->address, lo, hi);
+}
+
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+        struct thresh_restart tr = {
+                .b                      = b,
+                .set_lvt_off            = 1,
+                .lvt_off                = offset,
+        };
+
+        b->threshold_limit              = THRESHOLD_MAX;
+        threshold_restart_bank(&tr);
+};
+
+static int setup_APIC_mce(int reserved, int new)
+{
+        if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+                                              APIC_EILVT_MSG_FIX, 0))
+                return new;
+
+        return reserved;
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
+        struct threshold_block b;
         unsigned int cpu = smp_processor_id();
         u32 low = 0, high = 0, address = 0;
         unsigned int bank, block;
-        struct thresh_restart tr;
-        int lvt_off = -1;
-        u8 offset;
+        int offset = -1;
 
         for (bank = 0; bank < NR_BANKS; ++bank) {
                 for (block = 0; block < NR_BLOCKS; ++block) {
@@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
                         if (shared_bank[bank] && c->cpu_core_id)
                                 break;
 #endif
-                        offset = (high & MASK_LVTOFF_HI) >> 20;
-                        if (lvt_off < 0) {
-                                if (setup_APIC_eilvt(offset,
-                                                     THRESHOLD_APIC_VECTOR,
-                                                     APIC_EILVT_MSG_FIX, 0)) {
-                                        pr_err(FW_BUG "cpu %d, failed to "
-                                               "setup threshold interrupt "
-                                               "for bank %d, block %d "
-                                               "(MSR%08X=0x%x%08x)",
-                                               smp_processor_id(), bank, block,
-                                               address, high, low);
-                                        continue;
-                                }
-                                lvt_off = offset;
-                        } else if (lvt_off != offset) {
-                                pr_err(FW_BUG "cpu %d, invalid threshold "
-                                       "interrupt offset %d for bank %d,"
-                                       "block %d (MSR%08X=0x%x%08x)",
-                                       smp_processor_id(), lvt_off, bank,
-                                       block, address, high, low);
-                                continue;
-                        }
-
-                        high &= ~MASK_LVTOFF_HI;
-                        high |= lvt_off << 20;
-                        wrmsr(address, low, high);
+                        offset = setup_APIC_mce(offset,
+                                                (high & MASK_LVTOFF_HI) >> 20);
 
-                        threshold_defaults.address = address;
-                        tr.b = &threshold_defaults;
-                        tr.reset = 0;
-                        tr.old_limit = 0;
-                        threshold_restart_bank(&tr);
+                        memset(&b, 0, sizeof(b));
+                        b.cpu           = cpu;
+                        b.bank          = bank;
+                        b.block         = block;
+                        b.address       = address;
 
+                        mce_threshold_block_init(&b, offset);
                         mce_threshold_vector = amd_threshold_interrupt;
                 }
         }
@@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
 
         b->interrupt_enable = !!new;
 
+        memset(&tr, 0, sizeof(tr));
         tr.b            = b;
-        tr.reset        = 0;
-        tr.old_limit    = 0;
 
         smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
         if (new < 1)
                 new = 1;
 
+        memset(&tr, 0, sizeof(tr));
         tr.old_limit = b->threshold_limit;
         b->threshold_limit = new;
         tr.b = b;
-        tr.reset = 0;
 
         smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
                         continue;
                 err = threshold_create_bank(cpu, bank);
                 if (err)
-                        goto out;
+                        return err;
         }
-out:
+
         return err;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 6fcd0936194f..8694ef56459d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -130,7 +130,7 @@ void cmci_recheck(void)
         unsigned long flags;
         int banks;
 
-        if (!mce_available(&current_cpu_data) || !cmci_supported(&banks))
+        if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
                 return;
         local_irq_save(flags);
         machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4b683267eca5..e12246ff5aa6 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -53,8 +53,13 @@ struct thermal_state {
         struct _thermal_state core_power_limit;
         struct _thermal_state package_throttle;
         struct _thermal_state package_power_limit;
+        struct _thermal_state core_thresh0;
+        struct _thermal_state core_thresh1;
 };
 
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en  = ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
         return 0;
 }
 
+static int thresh_event_valid(int event)
+{
+        struct _thermal_state *state;
+        unsigned int this_cpu = smp_processor_id();
+        struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+        u64 now = get_jiffies_64();
+
+        state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+        if (time_before64(now, state->next_check))
+                return 0;
+
+        state->next_check = now + CHECK_INTERVAL;
+        return 1;
+}
+
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
 #define PACKAGE_THROTTLED       ((__u64)2 << 62)
 #define PACKAGE_POWER_LIMIT     ((__u64)3 << 62)
 
+static void notify_thresholds(__u64 msr_val)
+{
+        /* check whether the interrupt handler is defined;
+         * otherwise simply return
+         */
+        if (!platform_thermal_notify)
+                return;
+
+        /* lower threshold reached */
+        if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0))
+                platform_thermal_notify(msr_val);
+        /* higher threshold reached */
+        if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+                platform_thermal_notify(msr_val);
+}
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
 
         rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
+        /* Check for violation of core thermal thresholds*/
+        notify_thresholds(msr_val);
+
         if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
                                 THERMAL_THROTTLING_EVENT,
                                 CORE_LEVEL) != 0)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6d75b9145b13..9d977a2ea693 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void)
 {
         int i;
 
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                disable_lapic_nmi_watchdog();
-
         for (i = 0; i < x86_pmu.num_counters; i++) {
                 if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
                         goto perfctr_fail;
@@ -355,9 +352,6 @@ perfctr_fail:
         for (i--; i >= 0; i--)
                 release_perfctr_nmi(x86_pmu.perfctr + i);
 
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                enable_lapic_nmi_watchdog();
-
         return false;
 }
 
@@ -369,9 +363,6 @@ static void release_pmc_hardware(void)
                 release_perfctr_nmi(x86_pmu.perfctr + i);
                 release_evntsel_nmi(x86_pmu.eventsel + i);
         }
-
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                enable_lapic_nmi_watchdog();
 }
 
 #else
@@ -384,15 +375,53 @@ static void release_pmc_hardware(void) {}
 static bool check_hw_exists(void)
 {
         u64 val, val_new = 0;
-        int ret = 0;
+        int i, reg, ret = 0;
+
+        /*
+         * Check to see if the BIOS enabled any of the counters, if so
+         * complain and bail.
+         */
+        for (i = 0; i < x86_pmu.num_counters; i++) {
+                reg = x86_pmu.eventsel + i;
+                ret = rdmsrl_safe(reg, &val);
+                if (ret)
+                        goto msr_fail;
+                if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+                        goto bios_fail;
+        }
 
+        if (x86_pmu.num_counters_fixed) {
+                reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+                ret = rdmsrl_safe(reg, &val);
+                if (ret)
+                        goto msr_fail;
+                for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+                        if (val & (0x03 << i*4))
+                                goto bios_fail;
+                }
+        }
+
+        /*
+         * Now write a value and read it back to see if it matches,
+         * this is needed to detect certain hardware emulators (qemu/kvm)
+         * that don't trap on the MSR access and always return 0s.
+         */
         val = 0xabcdUL;
-        ret |= checking_wrmsrl(x86_pmu.perfctr, val);
+        ret = checking_wrmsrl(x86_pmu.perfctr, val);
         ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
         if (ret || val != val_new)
-                return false;
+                goto msr_fail;
 
         return true;
+
+bios_fail:
+        printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+        printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
+        return false;
+
+msr_fail:
+        printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+        return false;
 }
 
 static void reserve_ds_buffers(void);
@@ -451,7 +480,7 @@ static int x86_setup_perfctr(struct perf_event *event)
         struct hw_perf_event *hwc = &event->hw;
         u64 config;
 
-        if (!hwc->sample_period) {
+        if (!is_sampling_event(event)) {
                 hwc->sample_period = x86_pmu.max_period;
                 hwc->last_period = hwc->sample_period;
                 local64_set(&hwc->period_left, hwc->sample_period);
@@ -968,8 +997,7 @@ x86_perf_event_set_period(struct perf_event *event)
 
 static void x86_pmu_enable_event(struct perf_event *event)
 {
-        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-        if (cpuc->enabled)
+        if (__this_cpu_read(cpu_hw_events.enabled))
                 __x86_pmu_enable_event(&event->hw,
                                        ARCH_PERFMON_EVENTSEL_ENABLE);
 }
@@ -1239,11 +1267,10 @@ perf_event_nmi_handler(struct notifier_block *self,
 
         switch (cmd) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 break;
         case DIE_NMIUNKNOWN:
                 this_nmi = percpu_read(irq_stat.__nmi_count);
-                if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+                if (this_nmi != __this_cpu_read(pmu_nmi.marked))
                         /* let the kernel handle the unknown nmi */
                         return NOTIFY_DONE;
                 /*
@@ -1267,8 +1294,8 @@ perf_event_nmi_handler(struct notifier_block *self,
         this_nmi = percpu_read(irq_stat.__nmi_count);
         if ((handled > 1) ||
                 /* the next nmi could be a back-to-back nmi */
-            ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
-             (__get_cpu_var(pmu_nmi).handled > 1))) {
+            ((__this_cpu_read(pmu_nmi.marked) == this_nmi) &&
+             (__this_cpu_read(pmu_nmi.handled) > 1))) {
                 /*
                  * We could have two subsequent back-to-back nmis: The
                  * first handles more than one counter, the 2nd
@@ -1279,8 +1306,8 @@ perf_event_nmi_handler(struct notifier_block *self,
                  * handling more than one counter. We will mark the
                  * next (3rd) and then drop it if unhandled.
                  */
-                __get_cpu_var(pmu_nmi).marked   = this_nmi + 1;
-                __get_cpu_var(pmu_nmi).handled  = handled;
+                __this_cpu_write(pmu_nmi.marked, this_nmi + 1);
+                __this_cpu_write(pmu_nmi.handled, handled);
         }
 
         return NOTIFY_STOP;
@@ -1289,7 +1316,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
         .notifier_call          = perf_event_nmi_handler,
         .next                   = NULL,
-        .priority               = 1
+        .priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
@@ -1362,7 +1389,7 @@ static void __init pmu_check_apic(void)
         pr_info("no hardware sampling interrupt available.\n");
 }
 
-void __init init_hw_perf_events(void)
+int __init init_hw_perf_events(void)
 {
         struct event_constraint *c;
         int err;
@@ -1377,20 +1404,18 @@ void __init init_hw_perf_events(void)
                 err = amd_pmu_init();
                 break;
         default:
-                return;
+                return 0;
         }
         if (err != 0) {
                 pr_cont("no PMU driver, software events only.\n");
-                return;
+                return 0;
         }
 
         pmu_check_apic();
 
         /* sanity check that the hardware exists or is emulated */
-        if (!check_hw_exists()) {
-                pr_cont("Broken PMU hardware detected, software events only.\n");
-                return;
-        }
+        if (!check_hw_exists())
+                return 0;
 
         pr_cont("%s PMU driver.\n", x86_pmu.name);
 
@@ -1438,9 +1463,12 @@ void __init init_hw_perf_events(void)
         pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
         pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
-        perf_pmu_register(&pmu);
+        perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
         perf_cpu_notifier(x86_pmu_notifier);
+
+        return 0;
 }
+early_initcall(init_hw_perf_events);
 
 static inline void x86_pmu_read(struct perf_event *event)
 {
@@ -1454,11 +1482,9 @@ static inline void x86_pmu_read(struct perf_event *event)
  */
 static void x86_pmu_start_txn(struct pmu *pmu)
 {
-        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
         perf_pmu_disable(pmu);
-        cpuc->group_flag |= PERF_EVENT_TXN;
-        cpuc->n_txn = 0;
+        __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN);
+        __this_cpu_write(cpu_hw_events.n_txn, 0);
 }
 
 /*
@@ -1468,14 +1494,12 @@ static void x86_pmu_start_txn(struct pmu *pmu)
  */
 static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
-        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
-        cpuc->group_flag &= ~PERF_EVENT_TXN;
+        __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
         /*
          * Truncate the collected events.
          */
-        cpuc->n_added -= cpuc->n_txn;
-        cpuc->n_events -= cpuc->n_txn;
+        __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
+        __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
         perf_pmu_enable(pmu);
 }
 
@@ -1686,7 +1710,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
         perf_callchain_store(entry, regs->ip);
 
-        dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
+        dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index e421b8cd6944..67e2202a6039 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,7 +1,5 @@
 #ifdef CONFIG_CPU_SUP_AMD
 
-static DEFINE_RAW_SPINLOCK(amd_nb_lock);
-
 static __initconst const u64 amd_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
@@ -275,7 +273,7 @@ done:
         return &emptyconstraint;
 }
 
-static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
+static struct amd_nb *amd_alloc_nb(int cpu)
 {
         struct amd_nb *nb;
         int i;
@@ -285,7 +283,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
         if (!nb)
                 return NULL;
 
-        nb->nb_id = nb_id;
+        nb->nb_id = -1;
 
         /*
          * initialize all possible NB constraints
@@ -306,7 +304,7 @@ static int amd_pmu_cpu_prepare(int cpu)
         if (boot_cpu_data.x86_max_cores < 2)
                 return NOTIFY_OK;
 
-        cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+        cpuc->amd_nb = amd_alloc_nb(cpu);
         if (!cpuc->amd_nb)
                 return NOTIFY_BAD;
 
@@ -325,8 +323,6 @@ static void amd_pmu_cpu_starting(int cpu)
         nb_id = amd_get_nb_id(cpu);
         WARN_ON_ONCE(nb_id == BAD_APICID);
 
-        raw_spin_lock(&amd_nb_lock);
-
         for_each_online_cpu(i) {
                 nb = per_cpu(cpu_hw_events, i).amd_nb;
                 if (WARN_ON_ONCE(!nb))
@@ -341,8 +337,6 @@ static void amd_pmu_cpu_starting(int cpu)
 
         cpuc->amd_nb->nb_id = nb_id;
         cpuc->amd_nb->refcnt++;
-
-        raw_spin_unlock(&amd_nb_lock);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -354,8 +348,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
         cpuhw = &per_cpu(cpu_hw_events, cpu);
 
-        raw_spin_lock(&amd_nb_lock);
-
         if (cpuhw->amd_nb) {
                 struct amd_nb *nb = cpuhw->amd_nb;
 
@@ -364,8 +356,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
                 cpuhw->amd_nb = NULL;
         }
-
-        raw_spin_unlock(&amd_nb_lock);
 }
 
 static __initconst const struct x86_pmu amd_pmu = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c8f5c088cad1..008835c1d79c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -649,7 +649,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
         struct hw_perf_event *hwc = &event->hw;
 
         if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
-                if (!__get_cpu_var(cpu_hw_events).enabled)
+                if (!__this_cpu_read(cpu_hw_events.enabled))
                         return;
 
                 intel_pmu_enable_bts(hwc->config);
@@ -679,7 +679,7 @@ static int intel_pmu_save_and_restart(struct perf_event *event)
 
 static void intel_pmu_reset(void)
 {
-        struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
+        struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
         unsigned long flags;
         int idx;
 
@@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event)
         if (ret)
                 return ret;
 
+        if (event->attr.precise_ip &&
+            (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+                /*
+                 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+                 * (0x003c) so that we can use it with PEBS.
+                 *
+                 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+                 * PEBS capable. However we can use INST_RETIRED.ANY_P
+                 * (0x00c0), which is a PEBS capable event, to get the same
+                 * count.
+                 *
+                 * INST_RETIRED.ANY_P counts the number of cycles that retires
+                 * CNTMASK instructions. By setting CNTMASK to a value (16)
+                 * larger than the maximum number of instructions that can be
+                 * retired per cycle (4) and then inverting the condition, we
+                 * count all cycles that retire 16 or less instructions, which
+                 * is every cycle.
+                 *
+                 * Thereby we gain a PEBS capable cycle counter.
+                 */
+                u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+
+                alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+                event->hw.config = alt_config;
+        }
+
         if (event->attr.type != PERF_TYPE_RAW)
                 return 0;
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b93e694..e56b9bfbabd1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-        int overflow = 0;
-        u32 low, high;
+        u64 v;
 
-        rdmsr(hwc->config_base + hwc->idx, low, high);
-
-        /* we need to check high bit for unflagged overflows */
-        if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-                overflow = 1;
-                (void)checking_wrmsrl(hwc->config_base + hwc->idx,
-                        ((u64)low) & ~P4_CCCR_OVF);
+        /* an official way for overflow indication */
+        rdmsrl(hwc->config_base + hwc->idx, v);
+        if (v & P4_CCCR_OVF) {
+                wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+                return 1;
         }
 
-        return overflow;
+        /* it might be unflagged overflow */
+        rdmsrl(hwc->event_base + hwc->idx, v);
+        if (!(v & ARCH_P4_CNTRVAL_MASK))
+                return 1;
+
+        return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
          */
         .num_counters           = ARCH_P4_MAX_CCCR,
         .apic                   = 1,
-        .cntval_bits            = 40,
-        .cntval_mask            = (1ULL << 40) - 1,
-        .max_period             = (1ULL << 39) - 1,
+        .cntval_bits            = ARCH_P4_CNTRVAL_BITS,
+        .cntval_mask            = ARCH_P4_CNTRVAL_MASK,
+        .max_period             = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
         /*
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d9f4ff8fcd69..d5a236615501 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -16,32 +16,12 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
+#include <asm/nmi.h>
 #include <linux/kprobes.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
 
-struct nmi_watchdog_ctlblk {
-        unsigned int cccr_msr;
-        unsigned int perfctr_msr;  /* the MSR to reset in NMI handler */
-        unsigned int evntsel_msr;  /* the MSR to select the events to handle */
-};
-
-/* Interface defining a CPU specific perfctr watchdog */
-struct wd_ops {
-        int (*reserve)(void);
-        void (*unreserve)(void);
-        int (*setup)(unsigned nmi_hz);
-        void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz);
-        void (*stop)(void);
-        unsigned perfctr;
-        unsigned evntsel;
-        u64 checkbit;
-};
-
-static const struct wd_ops *wd_ops;
-
 /*
  * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
  * offset from MSR_P4_BSU_ESCR0.
@@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops;
 static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
 static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
 
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
-
 /* converts an msr to an appropriate reservation bit */
 static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 {
@@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr)
         clear_bit(counter, evntsel_nmi_owner);
 }
 EXPORT_SYMBOL(release_evntsel_nmi);
-
-void disable_lapic_nmi_watchdog(void)
-{
-        BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-        if (atomic_read(&nmi_active) <= 0)
-                return;
-
-        on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-
-        if (wd_ops)
-                wd_ops->unreserve();
-
-        BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-void enable_lapic_nmi_watchdog(void)
-{
-        BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-        /* are we already enabled */
-        if (atomic_read(&nmi_active) != 0)
-                return;
-
-        /* are we lapic aware */
-        if (!wd_ops)
-                return;
-        if (!wd_ops->reserve()) {
-                printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n");
-                return;
-        }
-
-        on_each_cpu(setup_apic_nmi_watchdog, NULL, 1);
-        touch_nmi_watchdog();
-}
-
-/*
- * Activate the NMI watchdog via the local APIC.
- */
-
-static unsigned int adjust_for_32bit_ctr(unsigned int hz)
-{
-        u64 counter_val;
-        unsigned int retval = hz;
-
-        /*
-         * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
-         * are writable, with higher bits sign extending from bit 31.
-         * So, we can only program the counter with 31 bit values and
-         * 32nd bit should be 1, for 33.. to be 1.
-         * Find the appropriate nmi_hz
-         */
-        counter_val = (u64)cpu_khz * 1000;
-        do_div(counter_val, retval);
-        if (counter_val > 0x7fffffffULL) {
-                u64 count = (u64)cpu_khz * 1000;
-                do_div(count, 0x7fffffffUL);
-                retval = count + 1;
-        }
-        return retval;
-}
-
-static void write_watchdog_counter(unsigned int perfctr_msr,
-                                const char *descr, unsigned nmi_hz)
-{
-        u64 count = (u64)cpu_khz * 1000;
-
-        do_div(count, nmi_hz);
-        if (descr)
-                pr_debug("setting %s to -0x%08Lx\n", descr, count);
-        wrmsrl(perfctr_msr, 0 - count);
-}
-
-static void write_watchdog_counter32(unsigned int perfctr_msr,
-                                const char *descr, unsigned nmi_hz)
-{
-        u64 count = (u64)cpu_khz * 1000;
-
-        do_div(count, nmi_hz);
-        if (descr)
-                pr_debug("setting %s to -0x%08Lx\n", descr, count);
-        wrmsr(perfctr_msr, (u32)(-count), 0);
-}
-
-/*
- * AMD K7/K8/Family10h/Family11h support.
- * AMD keeps this interface nicely stable so there is not much variety
- */
-#define K7_EVNTSEL_ENABLE       (1 << 22)
-#define K7_EVNTSEL_INT          (1 << 20)
-#define K7_EVNTSEL_OS           (1 << 17)
-#define K7_EVNTSEL_USR          (1 << 16)
-#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING    0x76
-#define K7_NMI_EVENT            K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
-
-static int setup_k7_watchdog(unsigned nmi_hz)
-{
-        unsigned int perfctr_msr, evntsel_msr;
-        unsigned int evntsel;
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-        perfctr_msr = wd_ops->perfctr;
-        evntsel_msr = wd_ops->evntsel;
-
-        wrmsrl(perfctr_msr, 0UL);
-
-        evntsel = K7_EVNTSEL_INT
-                | K7_EVNTSEL_OS
-                | K7_EVNTSEL_USR
-                | K7_NMI_EVENT;
-
-        /* setup the timer */
-        wrmsr(evntsel_msr, evntsel, 0);
-        write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz);
-
-        /* initialize the wd struct before enabling */
-        wd->perfctr_msr = perfctr_msr;
-        wd->evntsel_msr = evntsel_msr;
-        wd->cccr_msr = 0;  /* unused */
-
-        /* ok, everything is initialized, announce that we're set */
-        cpu_nmi_set_wd_enabled();
-
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= K7_EVNTSEL_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
-
-        return 1;
-}
-
-static void single_msr_stop_watchdog(void)
-{
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-        wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int single_msr_reserve(void)
-{
-        if (!reserve_perfctr_nmi(wd_ops->perfctr))
-                return 0;
-
-        if (!reserve_evntsel_nmi(wd_ops->evntsel)) {
-                release_perfctr_nmi(wd_ops->perfctr);
-                return 0;
-        }
-        return 1;
-}
-
-static void single_msr_unreserve(void)
-{
-        release_evntsel_nmi(wd_ops->evntsel);
-        release_perfctr_nmi(wd_ops->perfctr);
-}
-
-static void __kprobes
-single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-        /* start the cycle over again */
-        write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops k7_wd_ops = {
-        .reserve        = single_msr_reserve,
-        .unreserve      = single_msr_unreserve,
-        .setup          = setup_k7_watchdog,
-        .rearm          = single_msr_rearm,
-        .stop           = single_msr_stop_watchdog,
-        .perfctr        = MSR_K7_PERFCTR0,
-        .evntsel        = MSR_K7_EVNTSEL0,
-        .checkbit       = 1ULL << 47,
-};
-
-/*
- * Intel Model 6 (PPro+,P2,P3,P-M,Core1)
- */
-#define P6_EVNTSEL0_ENABLE      (1 << 22)
-#define P6_EVNTSEL_INT          (1 << 20)
-#define P6_EVNTSEL_OS           (1 << 17)
-#define P6_EVNTSEL_USR          (1 << 16)
-#define P6_EVENT_CPU_CLOCKS_NOT_HALTED  0x79
-#define P6_NMI_EVENT            P6_EVENT_CPU_CLOCKS_NOT_HALTED
-
-static int setup_p6_watchdog(unsigned nmi_hz)
-{
-        unsigned int perfctr_msr, evntsel_msr;
-        unsigned int evntsel;
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-        perfctr_msr = wd_ops->perfctr;
-        evntsel_msr = wd_ops->evntsel;
-
-        /* KVM doesn't implement this MSR */
-        if (wrmsr_safe(perfctr_msr, 0, 0) < 0)
-                return 0;
-
-        evntsel = P6_EVNTSEL_INT
-                | P6_EVNTSEL_OS
-                | P6_EVNTSEL_USR
-                | P6_NMI_EVENT;
-
-        /* setup the timer */
-        wrmsr(evntsel_msr, evntsel, 0);
-        nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-        write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz);
-
-        /* initialize the wd struct before enabling */
-        wd->perfctr_msr = perfctr_msr;
-        wd->evntsel_msr = evntsel_msr;
-        wd->cccr_msr = 0;  /* unused */
-
-        /* ok, everything is initialized, announce that we're set */
-        cpu_nmi_set_wd_enabled();
-
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= P6_EVNTSEL0_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
-
-        return 1;
-}
-
-static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-        /*
-         * P6 based Pentium M need to re-unmask
-         * the apic vector but it doesn't hurt
-         * other P6 variant.
-         * ArchPerfom/Core Duo also needs this
-         */
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-
-        /* P6/ARCH_PERFMON has 32 bit counter write */
-        write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p6_wd_ops = {
-        .reserve        = single_msr_reserve,
-        .unreserve      = single_msr_unreserve,
-        .setup          = setup_p6_watchdog,
-        .rearm          = p6_rearm,
-        .stop           = single_msr_stop_watchdog,
-        .perfctr        = MSR_P6_PERFCTR0,
-        .evntsel        = MSR_P6_EVNTSEL0,
-        .checkbit       = 1ULL << 39,
-};
-
-/*
- * Intel P4 performance counters.
- * By far the most complicated of all.
- */
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL   (1 << 7)
-#define P4_ESCR_EVENT_SELECT(N) ((N) << 25)
-#define P4_ESCR_OS              (1 << 3)
-#define P4_ESCR_USR             (1 << 2)
-#define P4_CCCR_OVF_PMI0        (1 << 26)
-#define P4_CCCR_OVF_PMI1        (1 << 27)
-#define P4_CCCR_THRESHOLD(N)    ((N) << 20)
-#define P4_CCCR_COMPLEMENT      (1 << 19)
-#define P4_CCCR_COMPARE         (1 << 18)
-#define P4_CCCR_REQUIRED        (3 << 16)
-#define P4_CCCR_ESCR_SELECT(N)  ((N) << 13)
-#define P4_CCCR_ENABLE          (1 << 12)
-#define P4_CCCR_OVF             (1 << 31)
-
-#define P4_CONTROLS 18
-static unsigned int p4_controls[18] = {
-        MSR_P4_BPU_CCCR0,
-        MSR_P4_BPU_CCCR1,
-        MSR_P4_BPU_CCCR2,
-        MSR_P4_BPU_CCCR3,
-        MSR_P4_MS_CCCR0,
-        MSR_P4_MS_CCCR1,
-        MSR_P4_MS_CCCR2,
-        MSR_P4_MS_CCCR3,
-        MSR_P4_FLAME_CCCR0,
-        MSR_P4_FLAME_CCCR1,
-        MSR_P4_FLAME_CCCR2,
-        MSR_P4_FLAME_CCCR3,
-        MSR_P4_IQ_CCCR0,
-        MSR_P4_IQ_CCCR1,
-        MSR_P4_IQ_CCCR2,
-        MSR_P4_IQ_CCCR3,
-        MSR_P4_IQ_CCCR4,
-        MSR_P4_IQ_CCCR5,
-};
-/*
- * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
- * CRU_ESCR0 (with any non-null event selector) through a complemented
- * max threshold. [IA32-Vol3, Section 14.9.9]
- */
-static int setup_p4_watchdog(unsigned nmi_hz)
-{
-        unsigned int perfctr_msr, evntsel_msr, cccr_msr;
-        unsigned int evntsel, cccr_val;
-        unsigned int misc_enable, dummy;
-        unsigned int ht_num;
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-        rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
-        if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
-                return 0;
-
-#ifdef CONFIG_SMP
-        /* detect which hyperthread we are on */
-        if (smp_num_siblings == 2) {
-                unsigned int ebx, apicid;
-
-                ebx = cpuid_ebx(1);
-                apicid = (ebx >> 24) & 0xff;
-                ht_num = apicid & 1;
-        } else
-#endif
-                ht_num = 0;
-
-        /*
-         * performance counters are shared resources
-         * assign each hyperthread its own set
-         * (re-use the ESCR0 register, seems safe
-         * and keeps the cccr_val the same)
-         */
-        if (!ht_num) {
-                /* logical cpu 0 */
-                perfctr_msr = MSR_P4_IQ_PERFCTR0;
-                evntsel_msr = MSR_P4_CRU_ESCR0;
-                cccr_msr = MSR_P4_IQ_CCCR0;
-                cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
-
-                /*
-                 * If we're on the kdump kernel or other situation, we may
-                 * still have other performance counter registers set to
-                 * interrupt and they'll keep interrupting forever because
-                 * of the P4_CCCR_OVF quirk. So we need to ACK all the
-                 * pending interrupts and disable all the registers here,
-                 * before reenabling the NMI delivery. Refer to p4_rearm()
-                 * about the P4_CCCR_OVF quirk.
-                 */
-                if (reset_devices) {
-                        unsigned int low, high;
-                        int i;
-
-                        for (i = 0; i < P4_CONTROLS; i++) {
-                                rdmsr(p4_controls[i], low, high);
-                                low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
-                                wrmsr(p4_controls[i], low, high);
-                        }
-                }
-        } else {
-                /* logical cpu 1 */
-                perfctr_msr = MSR_P4_IQ_PERFCTR1;
-                evntsel_msr = MSR_P4_CRU_ESCR0;
-                cccr_msr = MSR_P4_IQ_CCCR1;
-
-                /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */
-                if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4)
-                        cccr_val = P4_CCCR_OVF_PMI0;
-                else
-                        cccr_val = P4_CCCR_OVF_PMI1;
-                cccr_val |= P4_CCCR_ESCR_SELECT(4);
-        }
-
-        evntsel = P4_ESCR_EVENT_SELECT(0x3F)
-                | P4_ESCR_OS
-                | P4_ESCR_USR;
-
-        cccr_val |= P4_CCCR_THRESHOLD(15)
-                 | P4_CCCR_COMPLEMENT
-                 | P4_CCCR_COMPARE
-                 | P4_CCCR_REQUIRED;
-
-        wrmsr(evntsel_msr, evntsel, 0);
-        wrmsr(cccr_msr, cccr_val, 0);
-        write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-
-        wd->perfctr_msr = perfctr_msr;
-        wd->evntsel_msr = evntsel_msr;
-        wd->cccr_msr = cccr_msr;
-
-        /* ok, everything is initialized, announce that we're set */
-        cpu_nmi_set_wd_enabled();
-
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        cccr_val |= P4_CCCR_ENABLE;
-        wrmsr(cccr_msr, cccr_val, 0);
-        return 1;
-}
-
-static void stop_p4_watchdog(void)
-{
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-        wrmsr(wd->cccr_msr, 0, 0);
-        wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int p4_reserve(void)
-{
-        if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0))
-                return 0;
-#ifdef CONFIG_SMP
-        if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1))
-                goto fail1;
-#endif
-        if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
-                goto fail2;
-        /* RED-PEN why is ESCR1 not reserved here? */
-        return 1;
- fail2:
-#ifdef CONFIG_SMP
-        if (smp_num_siblings > 1)
-                release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
- fail1:
-#endif
-        release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
-        return 0;
-}
-
-static void p4_unreserve(void)
-{
-#ifdef CONFIG_SMP
-        if (smp_num_siblings > 1)
-                release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
-#endif
-        release_evntsel_nmi(MSR_P4_CRU_ESCR0);
-        release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
-}
-
-static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-        unsigned dummy;
-        /*
-         * P4 quirks:
-         * - An overflown perfctr will assert its interrupt
-         *   until the OVF flag in its CCCR is cleared.
-         * - LVTPC is masked on interrupt and must be
-         *   unmasked by the LVTPC handler.
-         */
-        rdmsrl(wd->cccr_msr, dummy);
-        dummy &= ~P4_CCCR_OVF;
-        wrmsrl(wd->cccr_msr, dummy);
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        /* start the cycle over again */
-        write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p4_wd_ops = {
-        .reserve        = p4_reserve,
-        .unreserve      = p4_unreserve,
-        .setup          = setup_p4_watchdog,
-        .rearm          = p4_rearm,
-        .stop           = stop_p4_watchdog,
-        /* RED-PEN this is wrong for the other sibling */
-        .perfctr        = MSR_P4_BPU_PERFCTR0,
-        .evntsel        = MSR_P4_BSU_ESCR0,
-        .checkbit       = 1ULL << 39,
-};
-
-/*
- * Watchdog using the Intel architected PerfMon.
- * Used for Core2 and hopefully all future Intel CPUs.
- */
-#define ARCH_PERFMON_NMI_EVENT_SEL      ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK    ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
-static struct wd_ops intel_arch_wd_ops;
-
-static int setup_intel_arch_watchdog(unsigned nmi_hz)
-{
-        unsigned int ebx;
-        union cpuid10_eax eax;
-        unsigned int unused;
-        unsigned int perfctr_msr, evntsel_msr;
-        unsigned int evntsel;
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-        /*
-         * Check whether the Architectural PerfMon supports
-         * Unhalted Core Cycles Event or not.
-         * NOTE: Corresponding bit = 0 in ebx indicates event present.
-         */
-        cpuid(10, &(eax.full), &ebx, &unused, &unused);
-        if ((eax.split.mask_length <
-                        (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
-            (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-                return 0;
-
-        perfctr_msr = wd_ops->perfctr;
-        evntsel_msr = wd_ops->evntsel;
-
-        wrmsrl(perfctr_msr, 0UL);
-
-        evntsel = ARCH_PERFMON_EVENTSEL_INT
-                | ARCH_PERFMON_EVENTSEL_OS
-                | ARCH_PERFMON_EVENTSEL_USR
-                | ARCH_PERFMON_NMI_EVENT_SEL
-                | ARCH_PERFMON_NMI_EVENT_UMASK;
-
-        /* setup the timer */
-        wrmsr(evntsel_msr, evntsel, 0);
-        nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-        write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-
-        wd->perfctr_msr = perfctr_msr;
-        wd->evntsel_msr = evntsel_msr;
-        wd->cccr_msr = 0;  /* unused */
-
-        /* ok, everything is initialized, announce that we're set */
-        cpu_nmi_set_wd_enabled();
-
-        apic_write(APIC_LVTPC, APIC_DM_NMI);
-        evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE;
-        wrmsr(evntsel_msr, evntsel, 0);
-        intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
-        return 1;
-}
-
-static struct wd_ops intel_arch_wd_ops __read_mostly = {
-        .reserve        = single_msr_reserve,
-        .unreserve      = single_msr_unreserve,
-        .setup          = setup_intel_arch_watchdog,
-        .rearm          = p6_rearm,
-        .stop           = single_msr_stop_watchdog,
-        .perfctr        = MSR_ARCH_PERFMON_PERFCTR1,
-        .evntsel        = MSR_ARCH_PERFMON_EVENTSEL1,
-};
-
-static void probe_nmi_watchdog(void)
-{
-        switch (boot_cpu_data.x86_vendor) {
-        case X86_VENDOR_AMD:
-                if (boot_cpu_data.x86 == 6 ||
-                    (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
-                        wd_ops = &k7_wd_ops;
-                return;
-        case X86_VENDOR_INTEL:
-                /* Work around where perfctr1 doesn't have a working enable
-                 * bit as described in the following errata:
-                 * AE49 Core Duo and Intel Core Solo 65 nm
-                 * AN49 Intel Pentium Dual-Core
-                 * AF49 Dual-Core Intel Xeon Processor LV
-                 */
-                if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) ||
-                    ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 &&
-                     boot_cpu_data.x86_mask == 4))) {
-                        intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
-                        intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
-                }
-                if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-                        wd_ops = &intel_arch_wd_ops;
-                        break;
-                }
-                switch (boot_cpu_data.x86) {
-                case 6:
-                        if (boot_cpu_data.x86_model > 13)
-                                return;
-
-                        wd_ops = &p6_wd_ops;
-                        break;
-                case 15:
-                        wd_ops = &p4_wd_ops;
-                        break;
-                default:
-                        return;
-                }
-                break;
-        }
-}
-
-/* Interface to nmi.c */
-
-int lapic_watchdog_init(unsigned nmi_hz)
-{
-        if (!wd_ops) {
-                probe_nmi_watchdog();
-                if (!wd_ops) {
-                        printk(KERN_INFO "NMI watchdog: CPU not supported\n");
-                        return -1;
-                }
-
-                if (!wd_ops->reserve()) {
-                        printk(KERN_ERR
-                                "NMI watchdog: cannot reserve perfctrs\n");
-                        return -1;
-                }
-        }
-
-        if (!(wd_ops->setup(nmi_hz))) {
-                printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n",
-                       raw_smp_processor_id());
-                return -1;
-        }
-
-        return 0;
-}
-
-void lapic_watchdog_stop(void)
-{
-        if (wd_ops)
-                wd_ops->stop();
-}
-
-unsigned lapic_adjust_nmi_hz(unsigned hz)
-{
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-        if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
-            wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1)
-                hz = adjust_for_32bit_ctr(hz);
-        return hz;
-}
-
-int __kprobes lapic_wd_event(unsigned nmi_hz)
-{
-        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-        u64 ctr;
-
-        rdmsrl(wd->perfctr_msr, ctr);
-        if (ctr & wd_ops->checkbit) /* perfctr still running? */
-                return 0;
-
-        wd_ops->rearm(wd, nmi_hz);
-        return 1;
-}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6e8752c1bd52..d6fb146c0d8b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
 
 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)
 {
         printk("%sCall Trace:\n", log_lvl);
-        dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+        dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp)
+                unsigned long *stack)
 {
-        show_trace_log_lvl(task, regs, stack, bp, "");
+        show_trace_log_lvl(task, regs, stack, "");
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-        show_stack_log_lvl(task, NULL, sp, 0, "");
+        show_stack_log_lvl(task, NULL, sp, "");
 }
 
 /*
@@ -197,20 +197,14 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
-        unsigned long bp = 0;
         unsigned long stack;
 
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp)
-                get_bp(bp);
-#endif
-
         printk("Pid: %d, comm: %.20s %s %s %.*s\n",
                 current->pid, current->comm, print_tainted(),
                 init_utsname()->release,
                 (int)strcspn(init_utsname()->version, " "),
                 init_utsname()->version);
-        show_trace(NULL, NULL, &stack, bp);
+        show_trace(NULL, NULL, &stack);
 }
 EXPORT_SYMBOL(dump_stack);
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 1bc7f75a5bda..74cc1eda384b 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,11 +17,12 @@
 #include <asm/stacktrace.h>
 
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+                struct pt_regs *regs, unsigned long *stack,
                 const struct stacktrace_ops *ops, void *data)
 {
         int graph = 0;
+        unsigned long bp;
 
         if (!task)
                 task = current;
@@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                         stack = (unsigned long *)task->thread.sp;
         }
 
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp) {
-                if (task == current) {
-                        /* Grab bp right from our regs */
-                        get_bp(bp);
-                } else {
-                        /* bp is the last reg pushed by switch_to */
-                        bp = *(unsigned long *) task->thread.sp;
-                }
-        }
-#endif
-
+        bp = stack_frame(task, regs);
         for (;;) {
                 struct thread_info *context;
 
@@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace);
 
 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)
 {
         unsigned long *stack;
         int i;
@@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
                 touch_nmi_watchdog();
         }
         printk(KERN_CONT "\n");
-        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+        show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 
@@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs)
                 u8 *ip;
 
                 printk(KERN_EMERG "Stack:\n");
-                show_stack_log_lvl(NULL, regs, &regs->sp,
-                                0, KERN_EMERG);
+                show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
 
                 printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6a340485249a..64101335de19 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+                struct pt_regs *regs, unsigned long *stack,
                 const struct stacktrace_ops *ops, void *data)
 {
         const unsigned cpu = get_cpu();
@@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
         unsigned used = 0;
         struct thread_info *tinfo;
         int graph = 0;
+        unsigned long bp;
 
         if (!task)
                 task = current;
@@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                         stack = (unsigned long *)task->thread.sp;
         }
 
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp) {
-                if (task == current) {
-                        /* Grab bp right from our regs */
-                        get_bp(bp);
-                } else {
-                        /* bp is the last reg pushed by switch_to */
-                        bp = *(unsigned long *) task->thread.sp;
-                }
-        }
-#endif
-
+        bp = stack_frame(task, regs);
         /*
          * Print function call entries in all stacks, starting at the
          * current stack address. If the stacks consist of nested
@@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
 
 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)
 {
         unsigned long *irq_stack_end;
         unsigned long *irq_stack;
@@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
         preempt_enable();
 
         printk(KERN_CONT "\n");
-        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+        show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 void show_registers(struct pt_regs *regs)
@@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs)
 
                 printk(KERN_EMERG "Stack:\n");
                 show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-                                regs->bp, KERN_EMERG);
+                                   KERN_EMERG);
 
                 printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 4572f25f9325..cd28a350f7f9 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -240,7 +240,7 @@ static int __init setup_early_printk(char *buf)
                 if (!strncmp(buf, "xen", 3))
                         early_console_register(&xenboot_console, keep);
 #endif
-#ifdef CONFIG_X86_MRST_EARLY_PRINTK
+#ifdef CONFIG_EARLY_PRINTK_MRST
                 if (!strncmp(buf, "mrst", 4)) {
                         mrst_early_console_init();
                         early_console_register(&early_mrst_console, keep);
@@ -250,7 +250,6 @@ static int __init setup_early_printk(char *buf)
                         hsu_early_console_init();
                         early_console_register(&early_hsu_console, keep);
                 }
-
 #endif
                 buf++;
         }
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e3ba417e8697..d3b895f375d3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -299,17 +299,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_args)
         XCPT_FRAME
         cld
-        movq_cfi rdi, RDI+16-ARGOFFSET
-        movq_cfi rsi, RSI+16-ARGOFFSET
-        movq_cfi rdx, RDX+16-ARGOFFSET
-        movq_cfi rcx, RCX+16-ARGOFFSET
-        movq_cfi rax, RAX+16-ARGOFFSET
-        movq_cfi  r8,  R8+16-ARGOFFSET
-        movq_cfi  r9,  R9+16-ARGOFFSET
-        movq_cfi r10, R10+16-ARGOFFSET
-        movq_cfi r11, R11+16-ARGOFFSET
-
-        leaq -ARGOFFSET+16(%rsp),%rdi   /* arg1 for handler */
+        /*
+         * start from rbp in pt_regs and jump over
+         * return address.
+         */
+        movq_cfi rdi, RDI+8-RBP
+        movq_cfi rsi, RSI+8-RBP
+        movq_cfi rdx, RDX+8-RBP
+        movq_cfi rcx, RCX+8-RBP
+        movq_cfi rax, RAX+8-RBP
+        movq_cfi  r8,  R8+8-RBP
+        movq_cfi  r9,  R9+8-RBP
+        movq_cfi r10, R10+8-RBP
+        movq_cfi r11, R11+8-RBP
+
+        leaq -RBP+8(%rsp),%rdi  /* arg1 for handler */
         movq_cfi rbp, 8         /* push %rbp */
         leaq 8(%rsp), %rbp              /* mov %rsp, %ebp */
         testl $3, CS(%rdi)
@@ -782,8 +786,9 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
         .macro interrupt func
-        subq $ORIG_RAX-ARGOFFSET+8, %rsp
-        CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
+        /* reserve pt_regs for scratch regs and rbp */
+        subq $ORIG_RAX-RBP, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
         call save_args
         PARTIAL_FRAME 0
         call \func
@@ -808,9 +813,14 @@ ret_from_intr:
         TRACE_IRQS_OFF
         decl PER_CPU_VAR(irq_count)
         leaveq
+
         CFI_RESTORE             rbp
         CFI_DEF_CFA_REGISTER    rsp
         CFI_ADJUST_CFA_OFFSET   -8
+
+        /* we did not save rbx, restore only from ARGOFFSET */
+        addq $8, %rsp
+        CFI_ADJUST_CFA_OFFSET   -8
 exit_intr:
         GET_THREAD_INFO(%rcx)
         testl $3,CS-ARGOFFSET(%rsp)
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3afb33f14d2d..382eb2936d4d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/module.h>
 
 #include <trace/syscall.h>
 
@@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code);
 int ftrace_arch_code_modify_prepare(void)
 {
         set_kernel_text_rw();
+        set_all_modules_text_rw();
         modifying_code = 1;
         return 0;
 }
@@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void)
 int ftrace_arch_code_modify_post_process(void)
 {
         modifying_code = 0;
+        set_all_modules_text_ro();
         set_kernel_text_ro();
         return 0;
 }
@@ -167,9 +170,9 @@ static void ftrace_mod_code(void)
 
 void ftrace_nmi_enter(void)
 {
-        __get_cpu_var(save_modifying_code) = modifying_code;
+        __this_cpu_write(save_modifying_code, modifying_code);
 
-        if (!__get_cpu_var(save_modifying_code))
+        if (!__this_cpu_read(save_modifying_code))
                 return;
 
         if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
@@ -183,7 +186,7 @@ void ftrace_nmi_enter(void)
 
 void ftrace_nmi_exit(void)
 {
-        if (!__get_cpu_var(save_modifying_code))
+        if (!__this_cpu_read(save_modifying_code))
                 return;
 
         /* Finish all executions before clearing nmi_running */
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 763310165fa0..7f138b3c3c52 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -61,6 +61,9 @@ void __init i386_start_kernel(void)
         case X86_SUBARCH_MRST:
                 x86_mrst_early_setup();
                 break;
+        case X86_SUBARCH_CE4100:
+                x86_ce4100_early_setup();
+                break;
         default:
                 i386_default_early_setup();
                 break;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c0dbd9ac24f0..9f54b209c378 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -139,39 +139,6 @@ ENTRY(startup_32)
         movl %eax, pa(olpc_ofw_pgd)
 #endif
 
-#ifdef CONFIG_PARAVIRT
-        /* This is can only trip for a broken bootloader... */
-        cmpw $0x207, pa(boot_params + BP_version)
-        jb default_entry
-
-        /* Paravirt-compatible boot parameters.  Look to see what architecture
-                we're booting under. */
-        movl pa(boot_params + BP_hardware_subarch), %eax
-        cmpl $num_subarch_entries, %eax
-        jae bad_subarch
-
-        movl pa(subarch_entries)(,%eax,4), %eax
-        subl $__PAGE_OFFSET, %eax
-        jmp *%eax
-
-bad_subarch:
-WEAK(lguest_entry)
-WEAK(xen_entry)
-        /* Unknown implementation; there's really
-           nothing we can do at this point. */
-        ud2a
-
-        __INITDATA
-
-subarch_entries:
-        .long default_entry             /* normal x86/PC */
-        .long lguest_entry              /* lguest hypervisor */
-        .long xen_entry                 /* Xen hypervisor */
-        .long default_entry             /* Moorestown MID */
-num_subarch_entries = (. - subarch_entries) / 4
-.previous
-#endif /* CONFIG_PARAVIRT */
-
 /*
  * Initialize page tables.  This creates a PDE and a set of page
  * tables, which are located immediately beyond __brk_base.  The variable
@@ -181,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4
  *
  * Note that the stack is not yet set up!
  */
-default_entry:
 #ifdef CONFIG_X86_PAE
 
         /*
@@ -261,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
         movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
         movl %eax,pa(initial_page_table+0xffc)
 #endif
-        jmp 3f
+
+#ifdef CONFIG_PARAVIRT
+        /* This is can only trip for a broken bootloader... */
+        cmpw $0x207, pa(boot_params + BP_version)
+        jb default_entry
+
+        /* Paravirt-compatible boot parameters.  Look to see what architecture
+                we're booting under. */
+        movl pa(boot_params + BP_hardware_subarch), %eax
+        cmpl $num_subarch_entries, %eax
+        jae bad_subarch
+
+        movl pa(subarch_entries)(,%eax,4), %eax
+        subl $__PAGE_OFFSET, %eax
+        jmp *%eax
+
+bad_subarch:
+WEAK(lguest_entry)
+WEAK(xen_entry)
+        /* Unknown implementation; there's really
+           nothing we can do at this point. */
+        ud2a
+
+        __INITDATA
+
+subarch_entries:
+        .long default_entry             /* normal x86/PC */
+        .long lguest_entry              /* lguest hypervisor */
+        .long xen_entry                 /* Xen hypervisor */
+        .long default_entry             /* Moorestown MID */
+num_subarch_entries = (. - subarch_entries) / 4
+.previous
+#else
+        jmp default_entry
+#endif /* CONFIG_PARAVIRT */
+
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
@@ -282,7 +283,7 @@ ENTRY(startup_32_smp)
         movl %eax,%fs
         movl %eax,%gs
 #endif /* CONFIG_SMP */
-3:
+default_entry:
 
 /*
  *      New page tables may be in 4Mbyte page mode and may
@@ -316,6 +317,10 @@ ENTRY(startup_32_smp)
         subl $0x80000001, %eax
         cmpl $(0x8000ffff-0x80000001), %eax
         ja 6f
+
+        /* Clear bogus XD_DISABLE bits */
+        call verify_cpu
+
         mov $0x80000001, %eax
         cpuid
         /* Execute Disable bit supported? */
@@ -611,6 +616,8 @@ ignore_int:
 #endif
         iret
 
+#include "verify_cpu.S"
+
         __REFDATA
 .align 4
 ENTRY(initial_code)
@@ -622,13 +629,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
         .align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-ENTRY(initial_pg_pmd)
+initial_pg_pmd:
         .fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
         .fill 1024,4,0
 #endif
-ENTRY(initial_pg_fixmap)
+initial_pg_fixmap:
         .fill 1024,4,0
 ENTRY(empty_zero_page)
         .fill 4096,1,0
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 42c594254507..02f07634d265 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
                 return -EBUSY;
 
         set_debugreg(info->address, i);
-        __get_cpu_var(cpu_debugreg[i]) = info->address;
+        __this_cpu_write(cpu_debugreg[i], info->address);
 
         dr7 = &__get_cpu_var(cpu_dr7);
         *dr7 |= encode_dr7(i, info->len, info->type);
@@ -397,12 +397,12 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
 
 void hw_breakpoint_restore(void)
 {
-        set_debugreg(__get_cpu_var(cpu_debugreg[0]), 0);
-        set_debugreg(__get_cpu_var(cpu_debugreg[1]), 1);
-        set_debugreg(__get_cpu_var(cpu_debugreg[2]), 2);
-        set_debugreg(__get_cpu_var(cpu_debugreg[3]), 3);
+        set_debugreg(__this_cpu_read(cpu_debugreg[0]), 0);
+        set_debugreg(__this_cpu_read(cpu_debugreg[1]), 1);
+        set_debugreg(__this_cpu_read(cpu_debugreg[2]), 2);
+        set_debugreg(__this_cpu_read(cpu_debugreg[3]), 3);
         set_debugreg(current->thread.debugreg6, 6);
-        set_debugreg(__get_cpu_var(cpu_dr7), 7);
+        set_debugreg(__this_cpu_read(cpu_dr7), 7);
 }
 EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 83ec0175f986..3a43caa3beb7 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -234,7 +234,7 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
         exit_idle();
         irq_enter();
 
-        irq = __get_cpu_var(vector_irq)[vector];
+        irq = __this_cpu_read(vector_irq[vector]);
 
         if (!handle_irq(irq, regs)) {
                 ack_APIC_irq();
@@ -350,12 +350,12 @@ void fixup_irqs(void)
         for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
                 unsigned int irr;
 
-                if (__get_cpu_var(vector_irq)[vector] < 0)
+                if (__this_cpu_read(vector_irq[vector]) < 0)
                         continue;
 
                 irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
                 if (irr  & (1 << (vector % 32))) {
-                        irq = __get_cpu_var(vector_irq)[vector];
+                        irq = __this_cpu_read(vector_irq[vector]);
 
                         data = irq_get_irq_data(irq);
                         raw_spin_lock(&desc->lock);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 96656f207751..48ff6dcffa02 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -79,7 +79,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
         u32 *isp, arg1, arg2;
 
         curctx = (union irq_ctx *) current_thread_info();
-        irqctx = __get_cpu_var(hardirq_ctx);
+        irqctx = __this_cpu_read(hardirq_ctx);
 
         /*
          * this is where we switch to the IRQ stack. However, if we are
@@ -166,7 +166,7 @@ asmlinkage void do_softirq(void)
 
         if (local_softirq_pending()) {
                 curctx = current_thread_info();
-                irqctx = __get_cpu_var(softirq_ctx);
+                irqctx = __this_cpu_read(softirq_ctx);
                 irqctx->tinfo.task = curctx->task;
                 irqctx->tinfo.previous_esp = current_stack_pointer;
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index cd21b654dec6..a4130005028a 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -48,6 +48,7 @@
 #include <asm/apicdef.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 {
@@ -525,10 +526,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
                 }
                 return NOTIFY_DONE;
 
-        case DIE_NMI_IPI:
-                /* Just ignore, we will handle the roundup on DIE_NMI. */
-                return NOTIFY_DONE;
-
         case DIE_NMIUNKNOWN:
                 if (was_in_debug_nmi[raw_smp_processor_id()]) {
                         was_in_debug_nmi[raw_smp_processor_id()] = 0;
@@ -606,7 +603,7 @@ static struct notifier_block kgdb_notifier = {
         /*
          * Lowest-prio notifier priority, we want to be notified last:
          */
-        .priority       = -INT_MAX,
+        .priority       = NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1cbd54c0df99..d91c477b3f62 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -403,7 +403,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-        __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+        __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
         kcb->kprobe_status = kcb->prev_kprobe.status;
         kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags;
         kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
@@ -412,7 +412,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
                                 struct kprobe_ctlblk *kcb)
 {
-        __get_cpu_var(current_kprobe) = p;
+        __this_cpu_write(current_kprobe, p);
         kcb->kprobe_saved_flags = kcb->kprobe_old_flags
                 = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
         if (is_IF_modifier(p->ainsn.insn))
@@ -586,7 +586,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
                 preempt_enable_no_resched();
                 return 1;
         } else if (kprobe_running()) {
-                p = __get_cpu_var(current_kprobe);
+                p = __this_cpu_read(current_kprobe);
                 if (p->break_handler && p->break_handler(p, regs)) {
                         setup_singlestep(p, regs, kcb, 0);
                         return 1;
@@ -759,11 +759,11 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 
                 orig_ret_address = (unsigned long)ri->ret_addr;
                 if (ri->rp && ri->rp->handler) {
-                        __get_cpu_var(current_kprobe) = &ri->rp->kp;
+                        __this_cpu_write(current_kprobe, &ri->rp->kp);
                         get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
                         ri->ret_addr = correct_ret_addr;
                         ri->rp->handler(ri, regs);
-                        __get_cpu_var(current_kprobe) = NULL;
+                        __this_cpu_write(current_kprobe, NULL);
                 }
 
                 recycle_rp_inst(ri, &empty_rp);
@@ -1184,6 +1184,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 {
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+        /* This is possible if op is under delayed unoptimizing */
+        if (kprobe_disabled(&op->kp))
+                return;
+
         preempt_disable();
         if (kprobe_running()) {
                 kprobes_inc_nmissed_count(&op->kp);
@@ -1198,10 +1202,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
                 regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
                 regs->orig_ax = ~0UL;
 
-                __get_cpu_var(current_kprobe) = &op->kp;
+                __this_cpu_write(current_kprobe, &op->kp);
                 kcb->kprobe_status = KPROBE_HIT_ACTIVE;
                 opt_pre_handler(&op->kp, regs);
-                __get_cpu_var(current_kprobe) = NULL;
+                __this_cpu_write(current_kprobe, NULL);
         }
         preempt_enable_no_resched();
 }
@@ -1401,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
         return 0;
 }
 
-/* Replace a breakpoint (int3) with a relative jump.  */
-int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+        u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+                                            u8 *insn_buf,
+                                            struct optimized_kprobe *op)
 {
-        unsigned char jmp_code[RELATIVEJUMP_SIZE];
         s32 rel = (s32)((long)op->optinsn.insn -
                         ((long)op->kp.addr + RELATIVEJUMP_SIZE));
 
@@ -1412,16 +1422,79 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
         memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
                RELATIVE_ADDR_SIZE);
 
-        jmp_code[0] = RELATIVEJUMP_OPCODE;
-        *(s32 *)(&jmp_code[1]) = rel;
+        insn_buf[0] = RELATIVEJUMP_OPCODE;
+        *(s32 *)(&insn_buf[1]) = rel;
+
+        tprm->addr = op->kp.addr;
+        tprm->opcode = insn_buf;
+        tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+        struct optimized_kprobe *op, *tmp;
+        int c = 0;
+
+        list_for_each_entry_safe(op, tmp, oplist, list) {
+                WARN_ON(kprobe_disabled(&op->kp));
+                /* Setup param */
+                setup_optimize_kprobe(&jump_poke_params[c],
+                                      jump_poke_bufs[c].buf, op);
+                list_del_init(&op->list);
+                if (++c >= MAX_OPTIMIZE_PROBES)
+                        break;
+        }
 
         /*
          * text_poke_smp doesn't support NMI/MCE code modifying.
          * However, since kprobes itself also doesn't support NMI/MCE
          * code probing, it's not a problem.
          */
-        text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
-        return 0;
+        text_poke_smp_batch(jump_poke_params, c);
+}
+
+static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
+                                              u8 *insn_buf,
+                                              struct optimized_kprobe *op)
+{
+        /* Set int3 to first byte for kprobes */
+        insn_buf[0] = BREAKPOINT_INSTRUCTION;
+        memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+        tprm->addr = op->kp.addr;
+        tprm->opcode = insn_buf;
+        tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Recover original instructions and breakpoints from relative jumps.
+ * Caller must call with locking kprobe_mutex.
+ */
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+                                    struct list_head *done_list)
+{
+        struct optimized_kprobe *op, *tmp;
+        int c = 0;
+
+        list_for_each_entry_safe(op, tmp, oplist, list) {
+                /* Setup param */
+                setup_unoptimize_kprobe(&jump_poke_params[c],
+                                        jump_poke_bufs[c].buf, op);
+                list_move(&op->list, done_list);
+                if (++c >= MAX_OPTIMIZE_PROBES)
+                        break;
+        }
+
+        /*
+         * text_poke_smp doesn't support NMI/MCE code modifying.
+         * However, since kprobes itself also doesn't support NMI/MCE
+         * code probing, it's not a problem.
+         */
+        text_poke_smp_batch(jump_poke_params, c);
 }
 
 /* Replace a relative jump with a breakpoint (int3).  */
@@ -1453,11 +1526,35 @@ static int  __kprobes setup_detour_execution(struct kprobe *p,
         }
         return 0;
 }
+
+static int __kprobes init_poke_params(void)
+{
+        /* Allocate code buffer and parameter array */
+        jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+                                 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+        if (!jump_poke_bufs)
+                return -ENOMEM;
+
+        jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+                                   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+        if (!jump_poke_params) {
+                kfree(jump_poke_bufs);
+                jump_poke_bufs = NULL;
+                return -ENOMEM;
+        }
+
+        return 0;
+}
+#else   /* !CONFIG_OPTPROBES */
+static int __kprobes init_poke_params(void)
+{
+        return 0;
+}
 #endif
 
 int __init arch_init_kprobes(void)
 {
-        return 0;
+        return init_poke_params();
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ce0cb4721c9a..0fe6d1a66c38 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu)
         return 0;
 }
 
-static int get_ucode_data(void *to, const u8 *from, size_t n)
-{
-        memcpy(to, from, n);
-        return 0;
-}
-
 static void *
 get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 {
@@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
         u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
         void *mc;
 
-        if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR))
-                return NULL;
+        get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
 
         if (section_hdr[0] != UCODE_UCODE_TYPE) {
                 pr_err("error: invalid type field in container file section header\n");
@@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
                 return NULL;
         }
 
-        mc = vmalloc(UCODE_MAX_SIZE);
-        if (mc) {
-                memset(mc, 0, UCODE_MAX_SIZE);
-                if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR,
-                                   total_size)) {
-                        vfree(mc);
-                        mc = NULL;
-                } else
-                        *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
-        }
+        mc = vzalloc(UCODE_MAX_SIZE);
+        if (!mc)
+                return NULL;
+
+        get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
+        *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+
         return mc;
 }
 
@@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf)
         unsigned int *buf_pos = (unsigned int *)container_hdr;
         unsigned long size;
 
-        if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE))
-                return 0;
+        get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
 
         size = buf_pos[2];
 
@@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf)
         }
 
         buf += UCODE_CONTAINER_HEADER_SIZE;
-        if (get_ucode_data(equiv_cpu_table, buf, size)) {
-                vfree(equiv_cpu_table);
-                return 0;
-        }
+        get_ucode_data(equiv_cpu_table, buf, size);
 
         return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
 }
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 9af64d9c4b67..01b0f6d06451 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -118,21 +118,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 
 static void __init MP_ioapic_info(struct mpc_ioapic *m)
 {
-        if (!(m->flags & MPC_APIC_USABLE))
-                return;
-
-        printk(KERN_INFO "I/O APIC #%d Version %d at 0x%X.\n",
-               m->apicid, m->apicver, m->apicaddr);
-
-        mp_register_ioapic(m->apicid, m->apicaddr, gsi_top);
-}
-
-static void print_MP_intsrc_info(struct mpc_intsrc *m)
-{
-        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
-                " IRQ %02x, APIC ID %x, APIC INT %02x\n",
-                m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbus,
-                m->srcbusirq, m->dstapic, m->dstirq);
+        if (m->flags & MPC_APIC_USABLE)
+                mp_register_ioapic(m->apicid, m->apicaddr, gsi_top);
 }
 
 static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
@@ -144,73 +131,11 @@ static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
                 mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq);
 }
 
-static void __init assign_to_mp_irq(struct mpc_intsrc *m,
-                                    struct mpc_intsrc *mp_irq)
-{
-        mp_irq->dstapic = m->dstapic;
-        mp_irq->type = m->type;
-        mp_irq->irqtype = m->irqtype;
-        mp_irq->irqflag = m->irqflag;
-        mp_irq->srcbus = m->srcbus;
-        mp_irq->srcbusirq = m->srcbusirq;
-        mp_irq->dstirq = m->dstirq;
-}
-
-static void __init assign_to_mpc_intsrc(struct mpc_intsrc *mp_irq,
-                                        struct mpc_intsrc *m)
-{
-        m->dstapic = mp_irq->dstapic;
-        m->type = mp_irq->type;
-        m->irqtype = mp_irq->irqtype;
-        m->irqflag = mp_irq->irqflag;
-        m->srcbus = mp_irq->srcbus;
-        m->srcbusirq = mp_irq->srcbusirq;
-        m->dstirq = mp_irq->dstirq;
-}
-
-static int __init mp_irq_mpc_intsrc_cmp(struct mpc_intsrc *mp_irq,
-                                        struct mpc_intsrc *m)
-{
-        if (mp_irq->dstapic != m->dstapic)
-                return 1;
-        if (mp_irq->type != m->type)
-                return 2;
-        if (mp_irq->irqtype != m->irqtype)
-                return 3;
-        if (mp_irq->irqflag != m->irqflag)
-                return 4;
-        if (mp_irq->srcbus != m->srcbus)
-                return 5;
-        if (mp_irq->srcbusirq != m->srcbusirq)
-                return 6;
-        if (mp_irq->dstirq != m->dstirq)
-                return 7;
-
-        return 0;
-}
-
-static void __init MP_intsrc_info(struct mpc_intsrc *m)
-{
-        int i;
-
-        print_MP_intsrc_info(m);
-
-        for (i = 0; i < mp_irq_entries; i++) {
-                if (!mp_irq_mpc_intsrc_cmp(&mp_irqs[i], m))
-                        return;
-        }
-
-        assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
-        if (++mp_irq_entries == MAX_IRQ_SOURCES)
-                panic("Max # of irq sources exceeded!!\n");
-}
 #else /* CONFIG_X86_IO_APIC */
 static inline void __init MP_bus_info(struct mpc_bus *m) {}
 static inline void __init MP_ioapic_info(struct mpc_ioapic *m) {}
-static inline void __init MP_intsrc_info(struct mpc_intsrc *m) {}
 #endif /* CONFIG_X86_IO_APIC */
 
-
 static void __init MP_lintsrc_info(struct mpc_lintsrc *m)
 {
         apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x,"
@@ -222,7 +147,6 @@ static void __init MP_lintsrc_info(struct mpc_lintsrc *m)
 /*
  * Read/parse the MPC
  */
-
 static int __init smp_check_mpc(struct mpc_table *mpc, char *oem, char *str)
 {
 
@@ -275,18 +199,6 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
 
 void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
 
-static void __init smp_register_lapic_address(unsigned long address)
-{
-        mp_lapic_addr = address;
-
-        set_fixmap_nocache(FIX_APIC_BASE, address);
-        if (boot_cpu_physical_apicid == -1U) {
-                boot_cpu_physical_apicid  = read_apic_id();
-                apic_version[boot_cpu_physical_apicid] =
-                         GET_APIC_VERSION(apic_read(APIC_LVR));
-        }
-}
-
 static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 {
         char str[16];
@@ -301,17 +213,13 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 #ifdef CONFIG_X86_32
         generic_mps_oem_check(mpc, oem, str);
 #endif
-        /* save the local APIC address, it might be non-default */
+        /* Initialize the lapic mapping */
         if (!acpi_lapic)
-                mp_lapic_addr = mpc->lapic;
+                register_lapic_address(mpc->lapic);
 
         if (early)
                 return 1;
 
-        /* Initialize the lapic mapping */
-        if (!acpi_lapic)
-                smp_register_lapic_address(mpc->lapic);
-
         if (mpc->oemptr)
                 x86_init.mpparse.smp_read_mpc_oem(mpc);
 
@@ -337,7 +245,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
                         skip_entry(&mpt, &count, sizeof(struct mpc_ioapic));
                         break;
                 case MP_INTSRC:
-                        MP_intsrc_info((struct mpc_intsrc *)mpt);
+                        mp_save_irq((struct mpc_intsrc *)mpt);
                         skip_entry(&mpt, &count, sizeof(struct mpc_intsrc));
                         break;
                 case MP_LINTSRC:
@@ -429,13 +337,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 
                 intsrc.srcbusirq = i;
                 intsrc.dstirq = i ? i : 2;      /* IRQ0 to INTIN2 */
-                MP_intsrc_info(&intsrc);
+                mp_save_irq(&intsrc);
         }
 
         intsrc.irqtype = mp_ExtINT;
         intsrc.srcbusirq = 0;
         intsrc.dstirq = 0;      /* 8259A to INTIN0 */
-        MP_intsrc_info(&intsrc);
+        mp_save_irq(&intsrc);
 }
 
 
@@ -784,11 +692,11 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
         int i;
 
         apic_printk(APIC_VERBOSE, "OLD ");
-        print_MP_intsrc_info(m);
+        print_mp_irq_info(m);
 
         i = get_MP_intsrc_index(m);
         if (i > 0) {
-                assign_to_mpc_intsrc(&mp_irqs[i], m);
+                memcpy(m, &mp_irqs[i], sizeof(*m));
                 apic_printk(APIC_VERBOSE, "NEW ");
                 print_mp_irq_info(&mp_irqs[i]);
                 return;
@@ -875,14 +783,14 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
                 if (nr_m_spare > 0) {
                         apic_printk(APIC_VERBOSE, "*NEW* found\n");
                         nr_m_spare--;
-                        assign_to_mpc_intsrc(&mp_irqs[i], m_spare[nr_m_spare]);
+                        memcpy(m_spare[nr_m_spare], &mp_irqs[i], sizeof(mp_irqs[i]));
                         m_spare[nr_m_spare] = NULL;
                 } else {
                         struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
                         count += sizeof(struct mpc_intsrc);
                         if (check_slot(mpc_new_phys, mpc_new_length, count) < 0)
                                 goto out;
-                        assign_to_mpc_intsrc(&mp_irqs[i], m);
+                        memcpy(m, &mp_irqs[i], sizeof(*m));
                         mpc->length = count;
                         mpt += sizeof(struct mpc_intsrc);
                 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index ba0f0ca9f280..c01ffa5b9b87 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -143,7 +143,7 @@ static void flush_gart(void)
 
         spin_lock_irqsave(&iommu_bitmap_lock, flags);
         if (need_flush) {
-                k8_flush_garts();
+                amd_flush_garts();
                 need_flush = false;
         }
         spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
@@ -561,17 +561,17 @@ static void enable_gart_translations(void)
 {
         int i;
 
-        if (!k8_northbridges.gart_supported)
+        if (!amd_nb_has_feature(AMD_NB_GART))
                 return;
 
-        for (i = 0; i < k8_northbridges.num; i++) {
-                struct pci_dev *dev = k8_northbridges.nb_misc[i];
+        for (i = 0; i < amd_nb_num(); i++) {
+                struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
                 enable_gart_translation(dev, __pa(agp_gatt_table));
         }
 
         /* Flush the GART-TLB to remove stale entries */
-        k8_flush_garts();
+        amd_flush_garts();
 }
 
 /*
@@ -596,13 +596,13 @@ static void gart_fixup_northbridges(struct sys_device *dev)
         if (!fix_up_north_bridges)
                 return;
 
-        if (!k8_northbridges.gart_supported)
+        if (!amd_nb_has_feature(AMD_NB_GART))
                 return;
 
         pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-        for (i = 0; i < k8_northbridges.num; i++) {
-                struct pci_dev *dev = k8_northbridges.nb_misc[i];
+        for (i = 0; i < amd_nb_num(); i++) {
+                struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
                 /*
                  * Don't enable translations just yet.  That is the next
@@ -644,7 +644,7 @@ static struct sys_device device_gart = {
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
  */
-static __init int init_k8_gatt(struct agp_kern_info *info)
+static __init int init_amd_gatt(struct agp_kern_info *info)
 {
         unsigned aper_size, gatt_size, new_aper_size;
         unsigned aper_base, new_aper_base;
@@ -656,8 +656,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
         aper_size = aper_base = info->aper_size = 0;
         dev = NULL;
-        for (i = 0; i < k8_northbridges.num; i++) {
-                dev = k8_northbridges.nb_misc[i];
+        for (i = 0; i < amd_nb_num(); i++) {
+                dev = node_to_amd_nb(i)->misc;
                 new_aper_base = read_aperture(dev, &new_aper_size);
                 if (!new_aper_base)
                         goto nommu;
@@ -725,13 +725,13 @@ static void gart_iommu_shutdown(void)
         if (!no_agp)
                 return;
 
-        if (!k8_northbridges.gart_supported)
+        if (!amd_nb_has_feature(AMD_NB_GART))
                 return;
 
-        for (i = 0; i < k8_northbridges.num; i++) {
+        for (i = 0; i < amd_nb_num(); i++) {
                 u32 ctl;
 
-                dev = k8_northbridges.nb_misc[i];
+                dev = node_to_amd_nb(i)->misc;
                 pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
                 ctl &= ~GARTEN;
@@ -749,14 +749,14 @@ int __init gart_iommu_init(void)
         unsigned long scratch;
         long i;
 
-        if (!k8_northbridges.gart_supported)
+        if (!amd_nb_has_feature(AMD_NB_GART))
                 return 0;
 
 #ifndef CONFIG_AGP_AMD64
         no_agp = 1;
 #else
         /* Makefile puts PCI initialization via subsys_initcall first. */
-        /* Add other K8 AGP bridge drivers here */
+        /* Add other AMD AGP bridge drivers here */
         no_agp = no_agp ||
                 (agp_amd64_init() < 0) ||
                 (agp_copy_info(agp_bridge, &info) < 0);
@@ -765,7 +765,7 @@ int __init gart_iommu_init(void)
         if (no_iommu ||
             (!force_iommu && max_pfn <= MAX_DMA32_PFN) ||
             !gart_iommu_aperture ||
-            (no_agp && init_k8_gatt(&info) < 0)) {
+            (no_agp && init_amd_gatt(&info) < 0)) {
                 if (max_pfn > MAX_DMA32_PFN) {
                         pr_warning("More than 4GB of memory but GART IOMMU not available.\n");
                         pr_warning("falling back to iommu=soft.\n");
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b6472153e45b..7c23a0cd3eb9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -86,8 +86,7 @@ void exit_thread(void)
 void show_regs(struct pt_regs *regs)
 {
         show_registers(regs);
-        show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
-                   regs->bp);
+        show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
 }
 
 void show_regs_common(void)
@@ -369,6 +368,7 @@ void default_idle(void)
 {
         if (hlt_use_halt()) {
                 trace_power_start(POWER_CSTATE, 1, smp_processor_id());
+                trace_cpu_idle(1, smp_processor_id());
                 current_thread_info()->status &= ~TS_POLLING;
                 /*
                  * TS_POLLING-cleared state must be visible before we
@@ -439,8 +439,9 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
         trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id());
+        trace_cpu_idle((ax>>4)+1, smp_processor_id());
         if (!need_resched()) {
-                if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+                if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
                         clflush((void *)&current_thread_info()->flags);
 
                 __monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -455,7 +456,8 @@ static void mwait_idle(void)
 {
         if (!need_resched()) {
                 trace_power_start(POWER_CSTATE, 1, smp_processor_id());
-                if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+                trace_cpu_idle(1, smp_processor_id());
+                if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
                         clflush((void *)&current_thread_info()->flags);
 
                 __monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -476,10 +478,12 @@ static void mwait_idle(void)
 static void poll_idle(void)
 {
         trace_power_start(POWER_CSTATE, 0, smp_processor_id());
+        trace_cpu_idle(0, smp_processor_id());
         local_irq_enable();
         while (!need_resched())
                 cpu_relax();
-        trace_power_end(0);
+        trace_power_end(smp_processor_id());
+        trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 96586c3cbbbf..4b9befa0e347 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -113,8 +113,8 @@ void cpu_idle(void)
                         stop_critical_timings();
                         pm_idle();
                         start_critical_timings();
-
                         trace_power_end(smp_processor_id());
+                        trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
                 }
                 tick_nohz_restart_sched_tick();
                 preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b3d7a3a04f38..4c818a738396 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -142,6 +142,8 @@ void cpu_idle(void)
                         start_critical_timings();
 
                         trace_power_end(smp_processor_id());
+                        trace_cpu_idle(PWR_EVENT_EXIT,
+                                       smp_processor_id());
 
                         /* In many cases the interrupt that ended idle
                            has already called exit_idle. But some idle
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c495aa8d4815..fc7aae1e2bc7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -18,6 +18,7 @@
 #include <asm/pci_x86.h>
 #include <asm/virtext.h>
 #include <asm/cpu.h>
+#include <asm/nmi.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/ctype.h>
@@ -747,7 +748,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 {
         int cpu;
 
-        if (val != DIE_NMI_IPI)
+        if (val != DIE_NMI)
                 return NOTIFY_OK;
 
         cpu = raw_smp_processor_id();
@@ -778,6 +779,8 @@ static void smp_send_nmi_allbutself(void)
 
 static struct notifier_block crash_nmi_nb = {
         .notifier_call = crash_nmi_callback,
+        /* we want to be the first one called */
+        .priority = NMI_LOCAL_HIGH_PRIOR+1,
 };
 
 /* Halt all other CPUs, calling the specified function on each of them
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index fda313ebbb03..c8e41e90f59c 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -43,17 +43,33 @@ static void rdc321x_reset(struct pci_dev *dev)
         outb(1, 0x92);
 }
 
+static void ce4100_reset(struct pci_dev *dev)
+{
+        int i;
+
+        for (i = 0; i < 10; i++) {
+                outb(0x2, 0xcf9);
+                udelay(50);
+        }
+}
+
 struct device_fixup {
         unsigned int vendor;
         unsigned int device;
         void (*reboot_fixup)(struct pci_dev *);
 };
 
+/*
+ * PCI ids solely used for fixups_table go here
+ */
+#define PCI_DEVICE_ID_INTEL_CE4100      0x0708
+
 static const struct device_fixup fixups_table[] = {
 { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset },
 { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset },
 { PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset },
 { PCI_VENDOR_ID_RDC, PCI_DEVICE_ID_RDC_R6030, rdc321x_reset },
+{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CE4100, ce4100_reset },
 };
 
 /*
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a0f52af256a0..d3cfe26c0252 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -705,7 +705,7 @@ static u64 __init get_max_mapped(void)
 void __init setup_arch(char **cmdline_p)
 {
         int acpi = 0;
-        int k8 = 0;
+        int amd = 0;
         unsigned long flags;
 
 #ifdef CONFIG_X86_32
@@ -991,12 +991,12 @@ void __init setup_arch(char **cmdline_p)
         acpi = acpi_numa_init();
 #endif
 
-#ifdef CONFIG_K8_NUMA
+#ifdef CONFIG_AMD_NUMA
         if (!acpi)
-                k8 = !k8_numa_init(0, max_pfn);
+                amd = !amd_numa_init(0, max_pfn);
 #endif
 
-        initmem_init(0, max_pfn, acpi, k8);
+        initmem_init(0, max_pfn, acpi, amd);
         memblock_find_dma_reserve();
         dma32_reserve_bootmem();
 
@@ -1045,10 +1045,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
         init_apic_mappings();
-        ioapic_init_mappings();
-
-        /* need to wait for io_apic is mapped */
-        probe_nr_irqs_gsi();
+        ioapic_and_gsi_init();
 
         kvm_guest_init();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 083e99d1b7df..763df77343dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -97,12 +97,12 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
  */
 static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
 
-void cpu_hotplug_driver_lock()
+void cpu_hotplug_driver_lock(void)
 {
         mutex_lock(&x86_cpu_hotplug_driver_mutex);
 }
 
-void cpu_hotplug_driver_unlock()
+void cpu_hotplug_driver_unlock(void)
 {
         mutex_unlock(&x86_cpu_hotplug_driver_mutex);
 }
@@ -281,6 +281,13 @@ static void __cpuinit smp_callin(void)
          */
         smp_store_cpu_info(cpuid);
 
+        /*
+         * This must be done before setting cpu_online_mask
+         * or calling notify_cpu_starting.
+         */
+        set_cpu_sibling_map(raw_smp_processor_id());
+        wmb();
+
         notify_cpu_starting(cpuid);
 
         /*
@@ -316,16 +323,6 @@ notrace static void __cpuinit start_secondary(void *unused)
          */
         check_tsc_sync_target();
 
-        if (nmi_watchdog == NMI_IO_APIC) {
-                legacy_pic->mask(0);
-                enable_NMI_through_LVT0();
-                legacy_pic->unmask(0);
-        }
-
-        /* This must be done before setting cpu_online_mask */
-        set_cpu_sibling_map(raw_smp_processor_id());
-        wmb();
-
         /*
          * We need to hold call_lock, so there is no inconsistency
          * between the time smp_call_function() determines number of
@@ -430,7 +427,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 
         cpumask_set_cpu(cpu, c->llc_shared_map);
 
-        if (current_cpu_data.x86_max_cores == 1) {
+        if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
                 cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
                 c->booted_cores = 1;
                 return;
@@ -1061,8 +1058,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
                 printk(KERN_INFO "SMP mode deactivated.\n");
                 smpboot_clear_io_apic();
 
-                localise_nmi_watchdog();
-
                 connect_bsp_APIC();
                 setup_local_APIC();
                 end_local_APIC_setup();
@@ -1094,7 +1089,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
         preempt_disable();
         smp_cpu_index_default();
-        current_cpu_data = boot_cpu_data;
+        memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info));
         cpumask_copy(cpu_callin_mask, cpumask_of(0));
         mb();
         /*
@@ -1166,6 +1161,20 @@ out:
         preempt_enable();
 }
 
+void arch_disable_nonboot_cpus_begin(void)
+{
+        /*
+         * Avoid the smp alternatives switch during the disable_nonboot_cpus().
+         * In the suspend path, we will be back in the SMP mode shortly anyways.
+         */
+        skip_smp_alternatives = true;
+}
+
+void arch_disable_nonboot_cpus_end(void)
+{
+        skip_smp_alternatives = false;
+}
+
 void arch_enable_nonboot_cpus_begin(void)
 {
         set_mtrr_aps_delayed_init();
@@ -1196,7 +1205,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 #ifdef CONFIG_X86_IO_APIC
         setup_ioapic_dest();
 #endif
-        check_nmi_watchdog();
         mtrr_aps_init();
 }
 
@@ -1341,8 +1349,6 @@ int native_cpu_disable(void)
         if (cpu == 0)
                 return -EBUSY;
 
-        if (nmi_watchdog == NMI_LOCAL_APIC)
-                stop_apic_nmi_watchdog(NULL);
         clear_local_APIC();
 
         cpu_disable_common();
@@ -1377,7 +1383,7 @@ void play_dead_common(void)
 
         mb();
         /* Ack it */
-        __get_cpu_var(cpu_state) = CPU_DEAD;
+        __this_cpu_write(cpu_state, CPU_DEAD);
 
         /*
          * With physical CPU hotplug, we should halt the cpu
@@ -1397,11 +1403,11 @@ static inline void mwait_play_dead(void)
         int i;
         void *mwait_ptr;
 
-        if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
+        if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_MWAIT))
                 return;
-        if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+        if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH))
                 return;
-        if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+        if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
                 return;
 
         eax = CPUID_MWAIT_LEAF;
@@ -1452,7 +1458,7 @@ static inline void mwait_play_dead(void)
 
 static inline void hlt_play_dead(void)
 {
-        if (current_cpu_data.x86 >= 4)
+        if (__this_cpu_read(cpu_info.x86) >= 4)
                 wbinvd();
 
         while (1) {
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index b53c525368a7..938c8e10a19a 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-        dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
+        dump_trace(current, NULL, NULL, &save_stack_ops, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
-void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp)
+void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
 {
-        dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace);
+        dump_trace(current, regs, NULL, &save_stack_ops, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-        dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
+        dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
         if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index fb5cc5e14cfa..25a28a245937 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -22,10 +22,6 @@
 #include <asm/hpet.h>
 #include <asm/time.h>
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-int timer_ack;
-#endif
-
 #ifdef CONFIG_X86_64
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
 #endif
@@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
         /* Keep nmi watchdog up to date */
         inc_irq_stat(irq0_irqs);
 
-        /* Optimized out for !IO_APIC and x86_64 */
-        if (timer_ack) {
-                /*
-                 * Subtle, when I/O APICs are used we have to ack timer IRQ
-                 * manually to deassert NMI lines for the watchdog if run
-                 * on an 82489DX-based system.
-                 */
-                raw_spin_lock(&i8259A_lock);
-                outb(0x0c, PIC_MASTER_OCW3);
-                /* Ack the IRQ; AEOI will end it automatically. */
-                inb(PIC_MASTER_POLL);
-                raw_spin_unlock(&i8259A_lock);
-        }
-
         global_clock_event->event_handler(global_clock_event);
 
         /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 3af2dff58b21..075d130efcf9 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -127,7 +127,7 @@ startup_64:
 no_longmode:
         hlt
         jmp no_longmode
-#include "verify_cpu_64.S"
+#include "verify_cpu.S"
 
         # Careful these need to be in the same 64K segment as the above;
 tidt:
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index cb838ca42c96..b9b67166f9de 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -83,6 +83,13 @@ EXPORT_SYMBOL_GPL(used_vectors);
 
 static int ignore_nmis;
 
+int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
+
 static inline void conditional_sti(struct pt_regs *regs)
 {
         if (regs->flags & X86_EFLAGS_IF)
@@ -300,16 +307,23 @@ gp_in_kernel:
         die("general protection fault", regs, error_code);
 }
 
-static notrace __kprobes void
-mem_parity_error(unsigned char reason, struct pt_regs *regs)
+static int __init setup_unknown_nmi_panic(char *str)
 {
-        printk(KERN_EMERG
-                "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-                        reason, smp_processor_id());
+        unknown_nmi_panic = 1;
+        return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
-        printk(KERN_EMERG
-                "You have some hardware problem, likely on the PCI bus.\n");
+static notrace __kprobes void
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
+{
+        pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
 
+        /*
+         * On some machines, PCI SERR line is used to report memory
+         * errors. EDAC makes use of it.
+         */
 #if defined(CONFIG_EDAC)
         if (edac_handler_set()) {
                 edac_atomic_assert_error();
@@ -320,11 +334,11 @@ mem_parity_error(unsigned char reason, struct pt_regs *regs)
         if (panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
-        printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+        pr_emerg("Dazed and confused, but trying to continue\n");
 
-        /* Clear and disable the memory parity error line. */
-        reason = (reason & 0xf) | 4;
-        outb(reason, 0x61);
+        /* Clear and disable the PCI SERR error line. */
+        reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+        outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -332,22 +346,26 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 {
         unsigned long i;
 
-        printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
+        pr_emerg(
+        "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
         show_registers(regs);
 
         if (panic_on_io_nmi)
                 panic("NMI IOCK error: Not continuing");
 
         /* Re-enable the IOCK line, wait for a few seconds */
-        reason = (reason & 0xf) | 8;
-        outb(reason, 0x61);
+        reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+        outb(reason, NMI_REASON_PORT);
 
-        i = 2000;
-        while (--i)
-                udelay(1000);
+        i = 20000;
+        while (--i) {
+                touch_nmi_watchdog();
+                udelay(100);
+        }
 
-        reason &= ~8;
-        outb(reason, 0x61);
+        reason &= ~NMI_REASON_CLEAR_IOCHK;
+        outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -366,69 +384,50 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
                 return;
         }
 #endif
-        printk(KERN_EMERG
-                "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-                        reason, smp_processor_id());
+        pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
 
-        printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
-        if (panic_on_unrecovered_nmi)
+        pr_emerg("Do you have a strange power saving mode enabled?\n");
+        if (unknown_nmi_panic || panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
-        printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+        pr_emerg("Dazed and confused, but trying to continue\n");
 }
 
 static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 {
         unsigned char reason = 0;
-        int cpu;
 
-        cpu = smp_processor_id();
-
-        /* Only the BSP gets external NMIs from the system. */
-        if (!cpu)
-                reason = get_nmi_reason();
-
-        if (!(reason & 0xc0)) {
-                if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
-                                                                == NOTIFY_STOP)
-                        return;
+        /*
+         * CPU-specific NMI must be processed before non-CPU-specific
+         * NMI, otherwise we may lose it, because the CPU-specific
+         * NMI can not be detected/processed on other CPUs.
+         */
+        if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
+                return;
 
-#ifdef CONFIG_X86_LOCAL_APIC
-                if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-                                                        == NOTIFY_STOP)
-                        return;
+        /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+        raw_spin_lock(&nmi_reason_lock);
+        reason = get_nmi_reason();
 
-#ifndef CONFIG_LOCKUP_DETECTOR
+        if (reason & NMI_REASON_MASK) {
+                if (reason & NMI_REASON_SERR)
+                        pci_serr_error(reason, regs);
+                else if (reason & NMI_REASON_IOCHK)
+                        io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
                 /*
-                 * Ok, so this is none of the documented NMI sources,
-                 * so it must be the NMI watchdog.
+                 * Reassert NMI in case it became active
+                 * meanwhile as it's edge-triggered:
                  */
-                if (nmi_watchdog_tick(regs, reason))
-                        return;
-                if (!do_nmi_callback(regs, cpu))
-#endif /* !CONFIG_LOCKUP_DETECTOR */
-                        unknown_nmi_error(reason, regs);
-#else
-                unknown_nmi_error(reason, regs);
+                reassert_nmi();
 #endif
-
+                raw_spin_unlock(&nmi_reason_lock);
                 return;
         }
-        if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
-                return;
+        raw_spin_unlock(&nmi_reason_lock);
 
-        /* AK: following checks seem to be broken on modern chipsets. FIXME */
-        if (reason & 0x80)
-                mem_parity_error(reason, regs);
-        if (reason & 0x40)
-                io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-        /*
-         * Reassert NMI in case it became active meanwhile
-         * as it's edge-triggered:
-         */
-        reassert_nmi();
-#endif
+        unknown_nmi_error(reason, regs);
 }
 
 dotraplinkage notrace __kprobes void
@@ -446,14 +445,12 @@ do_nmi(struct pt_regs *regs, long error_code)
 
 void stop_nmi(void)
 {
-        acpi_nmi_disable();
         ignore_nmis++;
 }
 
 void restart_nmi(void)
 {
         ignore_nmis--;
-        acpi_nmi_enable();
 }
 
 /* May run on IST stack. */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0c40d8b72416..823f79a17ad1 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -659,7 +659,7 @@ void restore_sched_clock_state(void)
 
         local_irq_save(flags);
 
-        __get_cpu_var(cyc2ns_offset) = 0;
+        __this_cpu_write(cyc2ns_offset, 0);
         offset = cyc2ns_suspend - sched_clock();
 
         for_each_possible_cpu(cpu)
@@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void)
 
         if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
                 return 0;
+
+        if (tsc_clocksource_reliable)
+                return 0;
         /*
          * Intel systems are normally all synchronized.
          * Exceptions must mark TSC as unstable:
@@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void)
         if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
                 /* assume multi socket systems are not synchronized: */
                 if (num_possible_cpus() > 1)
-                        tsc_unstable = 1;
+                        return 1;
         }
 
-        return tsc_unstable;
+        return 0;
+}
+
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomolies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
+{
+        static u64 tsc_start = -1, ref_start;
+        static int hpet;
+        u64 tsc_stop, ref_stop, delta;
+        unsigned long freq;
+
+        /* Don't bother refining TSC on unstable systems */
+        if (check_tsc_unstable())
+                goto out;
+
+        /*
+         * Since the work is started early in boot, we may be
+         * delayed the first time we expire. So set the workqueue
+         * again once we know timers are working.
+         */
+        if (tsc_start == -1) {
+                /*
+                 * Only set hpet once, to avoid mixing hardware
+                 * if the hpet becomes enabled later.
+                 */
+                hpet = is_hpet_enabled();
+                schedule_delayed_work(&tsc_irqwork, HZ);
+                tsc_start = tsc_read_refs(&ref_start, hpet);
+                return;
+        }
+
+        tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+        /* hpet or pmtimer available ? */
+        if (!hpet && !ref_start && !ref_stop)
+                goto out;
+
+        /* Check, whether the sampling was disturbed by an SMI */
+        if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+                goto out;
+
+        delta = tsc_stop - tsc_start;
+        delta *= 1000000LL;
+        if (hpet)
+                freq = calc_hpet_ref(delta, ref_start, ref_stop);
+        else
+                freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+        /* Make sure we're within 1% */
+        if (abs(tsc_khz - freq) > tsc_khz/100)
+                goto out;
+
+        tsc_khz = freq;
+        printk(KERN_INFO "Refined TSC clocksource calibration: "
+                "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+                                        (unsigned long)tsc_khz % 1000);
+
+out:
+        clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-static void __init init_tsc_clocksource(void)
+
+static int __init init_tsc_clocksource(void)
 {
+        if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz)
+                return 0;
+
         if (tsc_clocksource_reliable)
                 clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
         /* lower the rating if we already know its unstable: */
@@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void)
                 clocksource_tsc.rating = 0;
                 clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
         }
-        clocksource_register_khz(&clocksource_tsc, tsc_khz);
+        schedule_delayed_work(&tsc_irqwork, 0);
+        return 0;
 }
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
 
 void __init tsc_init(void)
 {
@@ -949,6 +1036,5 @@ void __init tsc_init(void)
                 mark_tsc_unstable("TSCs unsynchronized");
 
         check_system_tsc_reliable();
-        init_tsc_clocksource();
 }
 
diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu.S
index 56a8c2a867d9..0edefc19a113 100644
--- a/arch/x86/kernel/verify_cpu_64.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -7,6 +7,7 @@
  *      Copyright (c) 2007  Andi Kleen (ak@suse.de)
  *      Copyright (c) 2007  Eric Biederman (ebiederm@xmission.com)
  *      Copyright (c) 2007  Vivek Goyal (vgoyal@in.ibm.com)
+ *      Copyright (c) 2010  Kees Cook (kees.cook@canonical.com)
  *
  *      This source code is licensed under the GNU General Public License,
  *      Version 2.  See the file COPYING for more details.
@@ -14,18 +15,17 @@
  *      This is a common code for verification whether CPU supports
  *      long mode and SSE or not. It is not called directly instead this
  *      file is included at various places and compiled in that context.
- *      Following are the current usage.
+ *      This file is expected to run in 32bit code.  Currently:
  *
- *      This file is included by both 16bit and 32bit code.
+ *      arch/x86/boot/compressed/head_64.S: Boot cpu verification
+ *      arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ *      arch/x86/kernel/head_32.S: processor startup
  *
- *      arch/x86_64/boot/setup.S : Boot cpu verification (16bit)
- *      arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit)
- *      arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit)
- *      arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit)
- *
- *      verify_cpu, returns the status of cpu check in register %eax.
+ *      verify_cpu, returns the status of longmode and SSE in register %eax.
  *              0: Success    1: Failure
  *
+ *      On Intel, the XD_DISABLE flag will be cleared as a side-effect.
+ *
  *      The caller needs to check for the error code and take the action
  *      appropriately. Either display a message or halt.
  */
@@ -62,8 +62,41 @@ verify_cpu:
         cmpl    $0x444d4163,%ecx
         jnz     verify_cpu_noamd
         mov     $1,%di                  # cpu is from AMD
+        jmp     verify_cpu_check
 
 verify_cpu_noamd:
+        cmpl    $0x756e6547,%ebx        # GenuineIntel?
+        jnz     verify_cpu_check
+        cmpl    $0x49656e69,%edx
+        jnz     verify_cpu_check
+        cmpl    $0x6c65746e,%ecx
+        jnz     verify_cpu_check
+
+        # only call IA32_MISC_ENABLE when:
+        # family > 6 || (family == 6 && model >= 0xd)
+        movl    $0x1, %eax              # check CPU family and model
+        cpuid
+        movl    %eax, %ecx
+
+        andl    $0x0ff00f00, %eax       # mask family and extended family
+        shrl    $8, %eax
+        cmpl    $6, %eax
+        ja      verify_cpu_clear_xd     # family > 6, ok
+        jb      verify_cpu_check        # family < 6, skip
+
+        andl    $0x000f00f0, %ecx       # mask model and extended model
+        shrl    $4, %ecx
+        cmpl    $0xd, %ecx
+        jb      verify_cpu_check        # family == 6, model < 0xd, skip
+
+verify_cpu_clear_xd:
+        movl    $MSR_IA32_MISC_ENABLE, %ecx
+        rdmsr
+        btrl    $2, %edx                # clear MSR_IA32_MISC_ENABLE_XD_DISABLE
+        jnc     verify_cpu_check        # only write MSR if bit was changed
+        wrmsr
+
+verify_cpu_check:
         movl    $0x1,%eax               # Does the cpu have what it takes
         cpuid
         andl    $REQUIRED_MASK0,%edx
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e03530aebfd0..bf4700755184 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ jiffies_64 = jiffies;
 
 PHDRS {
         text PT_LOAD FLAGS(5);          /* R_E */
-        data PT_LOAD FLAGS(7);          /* RWE */
+        data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
         user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
@@ -116,6 +116,10 @@ SECTIONS
 
         EXCEPTION_TABLE(16) :text = 0x9090
 
+#if defined(CONFIG_DEBUG_RODATA)
+        /* .text should occupy whole number of pages */
+        . = ALIGN(PAGE_SIZE);
+#endif
         X64_ALIGN_DEBUG_RODATA_BEGIN
         RO_DATA(PAGE_SIZE)
         X64_ALIGN_DEBUG_RODATA_END
@@ -335,7 +339,7 @@ SECTIONS
                 __bss_start = .;
                 *(.bss..page_aligned)
                 *(.bss)
-                . = ALIGN(4);
+                . = ALIGN(PAGE_SIZE);
                 __bss_stop = .;
         }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b989e1f1e5d3..46a368cb651e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -976,7 +976,7 @@ static inline u64 nsec_to_cycles(u64 nsec)
         if (kvm_tsc_changes_freq())
                 printk_once(KERN_WARNING
                  "kvm: unreliable cycle conversion on adjustable rate TSC\n");
-        ret = nsec * __get_cpu_var(cpu_tsc_khz);
+        ret = nsec * __this_cpu_read(cpu_tsc_khz);
         do_div(ret, USEC_PER_SEC);
         return ret;
 }
@@ -1061,7 +1061,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
         local_irq_save(flags);
         kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
         kernel_ns = get_kernel_ns();
-        this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+        this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
 
         if (unlikely(this_tsc_khz == 0)) {
                 local_irq_restore(flags);
@@ -4427,7 +4427,7 @@ EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
 static void tsc_bad(void *info)
 {
-        __get_cpu_var(cpu_tsc_khz) = 0;
+        __this_cpu_write(cpu_tsc_khz, 0);
 }
 
 static void tsc_khz_changed(void *data)
@@ -4441,7 +4441,7 @@ static void tsc_khz_changed(void *data)
                 khz = cpufreq_quick_get(raw_smp_processor_id());
         if (!khz)
                 khz = tsc_khz;
-        __get_cpu_var(cpu_tsc_khz) = khz;
+        __this_cpu_write(cpu_tsc_khz, khz);
 }
 
 static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index e7d5382ef263..4f420c2f2d55 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -4,7 +4,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
-#include <asm/pgtable.h>
 
 /*G:020
  * Our story starts with the kernel booting into startup_32 in
@@ -38,113 +37,9 @@ ENTRY(lguest_entry)
         /* Set up the initial stack so we can run C code. */
         movl $(init_thread_union+THREAD_SIZE),%esp
 
-        call init_pagetables
-
         /* Jumps are relative: we're running __PAGE_OFFSET too low. */
         jmp lguest_init+__PAGE_OFFSET
 
-/*
- * Initialize page tables.  This creates a PDE and a set of page
- * tables, which are located immediately beyond __brk_base.  The variable
- * _brk_end is set up to point to the first "safe" location.
- * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end.
- *
- * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they
- * don't have a stack at this point, so we can't just use call and ret.
- */
-init_pagetables:
-#if PTRS_PER_PMD > 1
-#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
-#else
-#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
-#endif
-#define pa(X) ((X) - __PAGE_OFFSET)
-
-/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
-        PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
-#ifdef CONFIG_X86_PAE
-
-        /*
-         * In PAE mode initial_page_table is statically defined to contain
-         * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
-         * entries). The identity mapping is handled by pointing two PGD entries
-         * to the first kernel PMD.
-         *
-         * Note the upper half of each PMD or PTE are always zero at this stage.
-         */
-
-#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
-
-        xorl %ebx,%ebx                          /* %ebx is kept at zero */
-
-        movl $pa(__brk_base), %edi
-        movl $pa(initial_pg_pmd), %edx
-        movl $PTE_IDENT_ATTR, %eax
-10:
-        leal PDE_IDENT_ATTR(%edi),%ecx          /* Create PMD entry */
-        movl %ecx,(%edx)                        /* Store PMD entry */
-                                                /* Upper half already zero */
-        addl $8,%edx
-        movl $512,%ecx
-11:
-        stosl
-        xchgl %eax,%ebx
-        stosl
-        xchgl %eax,%ebx
-        addl $0x1000,%eax
-        loop 11b
-
-        /*
-         * End condition: we must map up to the end + MAPPING_BEYOND_END.
-         */
-        movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-        cmpl %ebp,%eax
-        jb 10b
-1:
-        addl $__PAGE_OFFSET, %edi
-        movl %edi, pa(_brk_end)
-        shrl $12, %eax
-        movl %eax, pa(max_pfn_mapped)
-
-        /* Do early initialization of the fixmap area */
-        movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
-        movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
-#else   /* Not PAE */
-
-page_pde_offset = (__PAGE_OFFSET >> 20);
-
-        movl $pa(__brk_base), %edi
-        movl $pa(initial_page_table), %edx
-        movl $PTE_IDENT_ATTR, %eax
-10:
-        leal PDE_IDENT_ATTR(%edi),%ecx          /* Create PDE entry */
-        movl %ecx,(%edx)                        /* Store identity PDE entry */
-        movl %ecx,page_pde_offset(%edx)         /* Store kernel PDE entry */
-        addl $4,%edx
-        movl $1024, %ecx
-11:
-        stosl
-        addl $0x1000,%eax
-        loop 11b
-        /*
-         * End condition: we must map up to the end + MAPPING_BEYOND_END.
-         */
-        movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-        cmpl %ebp,%eax
-        jb 10b
-        addl $__PAGE_OFFSET, %edi
-        movl %edi, pa(_brk_end)
-        shrl $12, %eax
-        movl %eax, pa(max_pfn_mapped)
-
-        /* Do early initialization of the fixmap area */
-        movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
-        movl %eax,pa(initial_page_table+0xffc)
-#endif
-        ret
-
 /*G:055
  * We create a macro which puts the assembler code between lgstart_ and lgend_
  * markers.  These templates are put in the .text section: they can't be
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index ff485d361182..fc45ba887d05 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -121,7 +121,7 @@ inline void __const_udelay(unsigned long xloops)
         asm("mull %%edx"
                 :"=d" (xloops), "=&a" (d0)
                 :"1" (xloops), "0"
-                (cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
+                (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
 
         __delay(++xloops);
 }
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 55543397a8a7..09df2f9a3d69 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -23,7 +23,7 @@ mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)    += testmmiotrace.o
 
 obj-$(CONFIG_NUMA)              += numa.o numa_$(BITS).o
-obj-$(CONFIG_K8_NUMA)           += k8topology_64.o
+obj-$(CONFIG_AMD_NUMA)          += amdtopology_64.o
 obj-$(CONFIG_ACPI_NUMA)         += srat_$(BITS).o
 
 obj-$(CONFIG_HAVE_MEMBLOCK)             += memblock.o
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/amdtopology_64.c
index 804a3b6c6e14..f21962c435ed 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -1,8 +1,8 @@
 /*
- * AMD K8 NUMA support.
+ * AMD NUMA support.
  * Discover the memory map and associated nodes.
  *
- * This version reads it directly from the K8 northbridge.
+ * This version reads it directly from the AMD northbridge.
  *
  * Copyright 2002,2003 Andi Kleen, SuSE Labs.
  */
@@ -27,6 +27,7 @@
 #include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
+static unsigned char __initdata nodeids[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
 
 static __init int find_northbridge(void)
@@ -57,7 +58,7 @@ static __init void early_get_boot_cpu_id(void)
 {
         /*
          * need to get the APIC ID of the BSP so can use that to
-         * create apicid_to_node in k8_scan_nodes()
+         * create apicid_to_node in amd_scan_nodes()
          */
 #ifdef CONFIG_X86_MPPARSE
         /*
@@ -66,23 +67,9 @@ static __init void early_get_boot_cpu_id(void)
         if (smp_found_config)
                 early_get_smp_config();
 #endif
-        early_init_lapic_mapping();
 }
 
-int __init k8_get_nodes(struct bootnode *physnodes)
-{
-        int i;
-        int ret = 0;
-
-        for_each_node_mask(i, nodes_parsed) {
-                physnodes[ret].start = nodes[i].start;
-                physnodes[ret].end = nodes[i].end;
-                ret++;
-        }
-        return ret;
-}
-
-int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
+int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 {
         unsigned long start = PFN_PHYS(start_pfn);
         unsigned long end = PFN_PHYS(end_pfn);
@@ -114,7 +101,7 @@ int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
                 base = read_pci_config(0, nb, 1, 0x40 + i*8);
                 limit = read_pci_config(0, nb, 1, 0x44 + i*8);
 
-                nodeid = limit & 7;
+                nodeids[i] = nodeid = limit & 7;
                 if ((base & 3) == 0) {
                         if (i < numnodes)
                                 pr_info("Skipping disabled node %d\n", i);
@@ -194,7 +181,77 @@ int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
         return 0;
 }
 
-int __init k8_scan_nodes(void)
+#ifdef CONFIG_NUMA_EMU
+static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
+        [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
+void __init amd_get_nodes(struct bootnode *physnodes)
+{
+        int i;
+
+        for_each_node_mask(i, nodes_parsed) {
+                physnodes[i].start = nodes[i].start;
+                physnodes[i].end = nodes[i].end;
+        }
+}
+
+static int __init find_node_by_addr(unsigned long addr)
+{
+        int ret = NUMA_NO_NODE;
+        int i;
+
+        for (i = 0; i < 8; i++)
+                if (addr >= nodes[i].start && addr < nodes[i].end) {
+                        ret = i;
+                        break;
+                }
+        return ret;
+}
+
+/*
+ * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be
+ * setup to represent the physical topology but reflect the emulated
+ * environment.  For each emulated node, the real node which it appears on is
+ * found and a fake pxm to nid mapping is created which mirrors the actual
+ * locality.  node_distance() then represents the correct distances between
+ * emulated nodes by using the fake acpi mappings to pxms.
+ */
+void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
+{
+        unsigned int bits;
+        unsigned int cores;
+        unsigned int apicid_base = 0;
+        int i;
+
+        bits = boot_cpu_data.x86_coreid_bits;
+        cores = 1 << bits;
+        early_get_boot_cpu_id();
+        if (boot_cpu_physical_apicid > 0)
+                apicid_base = boot_cpu_physical_apicid;
+
+        for (i = 0; i < nr_nodes; i++) {
+                int index;
+                int nid;
+                int j;
+
+                nid = find_node_by_addr(nodes[i].start);
+                if (nid == NUMA_NO_NODE)
+                        continue;
+
+                index = nodeids[nid] << bits;
+                if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE)
+                        for (j = apicid_base; j < cores + apicid_base; j++)
+                                fake_apicid_to_node[index + j] = i;
+#ifdef CONFIG_ACPI_NUMA
+                __acpi_map_pxm_to_node(nid, i);
+#endif
+        }
+        memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+}
+#endif /* CONFIG_NUMA_EMU */
+
+int __init amd_scan_nodes(void)
 {
         unsigned int bits;
         unsigned int cores;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c0e28a13de7d..947f42abe820 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
         /*
          * We just marked the kernel text read only above, now that
          * we are going to free part of that, we need to make that
-         * writeable first.
+         * writeable and non-executable first.
          */
+        set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
         set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
 
         printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 0e969f9f401b..f89b5bb4e93f 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -226,7 +226,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 
 static inline int is_kernel_text(unsigned long addr)
 {
-        if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
+        if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
                 return 1;
         return 0;
 }
@@ -912,6 +912,23 @@ void set_kernel_text_ro(void)
         set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 }
 
+static void mark_nxdata_nx(void)
+{
+        /*
+         * When this called, init has already been executed and released,
+         * so everything past _etext sould be NX.
+         */
+        unsigned long start = PFN_ALIGN(_etext);
+        /*
+         * This comes from is_kernel_text upper limit. Also HPAGE where used:
+         */
+        unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;
+
+        if (__supported_pte_mask & _PAGE_NX)
+                printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10);
+        set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
         unsigned long start = PFN_ALIGN(_text);
@@ -946,6 +963,7 @@ void mark_rodata_ro(void)
         printk(KERN_INFO "Testing CPA: write protecting again\n");
         set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 #endif
+        mark_nxdata_nx();
 }
 #endif
 
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index af3b6c8a436f..704a37cedddb 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
         e->trace.entries = e->trace_entries;
         e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
         e->trace.skip = 0;
-        save_stack_trace_bp(&e->trace, regs->bp);
+        save_stack_trace_regs(&e->trace, regs);
 
         /* Round address down to nearest 16 bytes */
         shadow_copy = kmemcheck_shadow_lookup(address
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 7ffc9b727efd..1e72102e80c9 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -260,30 +260,30 @@ void __init numa_init_array(void)
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
-static struct bootnode physnodes[MAX_NUMNODES] __initdata;
+static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata;
 static char *cmdline __initdata;
 
 static int __init setup_physnodes(unsigned long start, unsigned long end,
-                                        int acpi, int k8)
+                                        int acpi, int amd)
 {
-        int nr_nodes = 0;
         int ret = 0;
         int i;
 
+        memset(physnodes, 0, sizeof(physnodes));
 #ifdef CONFIG_ACPI_NUMA
         if (acpi)
-                nr_nodes = acpi_get_nodes(physnodes);
+                acpi_get_nodes(physnodes, start, end);
 #endif
-#ifdef CONFIG_K8_NUMA
-        if (k8)
-                nr_nodes = k8_get_nodes(physnodes);
+#ifdef CONFIG_AMD_NUMA
+        if (amd)
+                amd_get_nodes(physnodes);
 #endif
         /*
          * Basic sanity checking on the physical node map: there may be errors
-         * if the SRAT or K8 incorrectly reported the topology or the mem=
+         * if the SRAT or AMD code incorrectly reported the topology or the mem=
          * kernel parameter is used.
          */
-        for (i = 0; i < nr_nodes; i++) {
+        for (i = 0; i < MAX_NUMNODES; i++) {
                 if (physnodes[i].start == physnodes[i].end)
                         continue;
                 if (physnodes[i].start > end) {
@@ -298,17 +298,6 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
                         physnodes[i].start = start;
                 if (physnodes[i].end > end)
                         physnodes[i].end = end;
-        }
-
-        /*
-         * Remove all nodes that have no memory or were truncated because of the
-         * limited address range.
-         */
-        for (i = 0; i < nr_nodes; i++) {
-                if (physnodes[i].start == physnodes[i].end)
-                        continue;
-                physnodes[ret].start = physnodes[i].start;
-                physnodes[ret].end = physnodes[i].end;
                 ret++;
         }
 
@@ -324,6 +313,24 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
         return ret;
 }
 
+static void __init fake_physnodes(int acpi, int amd, int nr_nodes)
+{
+        int i;
+
+        BUG_ON(acpi && amd);
+#ifdef CONFIG_ACPI_NUMA
+        if (acpi)
+                acpi_fake_nodes(nodes, nr_nodes);
+#endif
+#ifdef CONFIG_AMD_NUMA
+        if (amd)
+                amd_fake_nodes(nodes, nr_nodes);
+#endif
+        if (!acpi && !amd)
+                for (i = 0; i < nr_cpu_ids; i++)
+                        numa_set_node(i, 0);
+}
+
 /*
  * Setups up nid to range from addr to addr + size.  If the end
  * boundary is greater than max_addr, then max_addr is used instead.
@@ -352,8 +359,7 @@ static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr)
  * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
  * to max_addr.  The return value is the number of nodes allocated.
  */
-static int __init split_nodes_interleave(u64 addr, u64 max_addr,
-                                                int nr_phys_nodes, int nr_nodes)
+static int __init split_nodes_interleave(u64 addr, u64 max_addr, int nr_nodes)
 {
         nodemask_t physnode_mask = NODE_MASK_NONE;
         u64 size;
@@ -384,7 +390,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
                 return -1;
         }
 
-        for (i = 0; i < nr_phys_nodes; i++)
+        for (i = 0; i < MAX_NUMNODES; i++)
                 if (physnodes[i].start != physnodes[i].end)
                         node_set(i, physnode_mask);
 
@@ -549,15 +555,13 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
  * numa=fake command-line option.
  */
 static int __init numa_emulation(unsigned long start_pfn,
-                        unsigned long last_pfn, int acpi, int k8)
+                        unsigned long last_pfn, int acpi, int amd)
 {
         u64 addr = start_pfn << PAGE_SHIFT;
         u64 max_addr = last_pfn << PAGE_SHIFT;
-        int num_phys_nodes;
         int num_nodes;
         int i;
 
-        num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
         /*
          * If the numa=fake command-line contains a 'M' or 'G', it represents
          * the fixed node size.  Otherwise, if it is just a single number N,
@@ -572,7 +576,7 @@ static int __init numa_emulation(unsigned long start_pfn,
                 unsigned long n;
 
                 n = simple_strtoul(cmdline, NULL, 0);
-                num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
+                num_nodes = split_nodes_interleave(addr, max_addr, n);
         }
 
         if (num_nodes < 0)
@@ -595,14 +599,15 @@ static int __init numa_emulation(unsigned long start_pfn,
                                                 nodes[i].end >> PAGE_SHIFT);
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
         }
-        acpi_fake_nodes(nodes, num_nodes);
+        setup_physnodes(addr, max_addr, acpi, amd);
+        fake_physnodes(acpi, amd, num_nodes);
         numa_init_array();
         return 0;
 }
 #endif /* CONFIG_NUMA_EMU */
 
 void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
-                                int acpi, int k8)
+                                int acpi, int amd)
 {
         int i;
 
@@ -610,8 +615,12 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
         nodes_clear(node_online_map);
 
 #ifdef CONFIG_NUMA_EMU
-        if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, k8))
+        setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+                        acpi, amd);
+        if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd))
                 return;
+        setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+                        acpi, amd);
         nodes_clear(node_possible_map);
         nodes_clear(node_online_map);
 #endif
@@ -624,8 +633,8 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
         nodes_clear(node_online_map);
 #endif
 
-#ifdef CONFIG_K8_NUMA
-        if (!numa_off && k8 && !k8_scan_nodes())
+#ifdef CONFIG_AMD_NUMA
+        if (!numa_off && amd && !amd_scan_nodes())
                 return;
         nodes_clear(node_possible_map);
         nodes_clear(node_online_map);
@@ -767,6 +776,7 @@ void __cpuinit numa_clear_node(int cpu)
 
 #ifndef CONFIG_DEBUG_PER_CPU_MAPS
 
+#ifndef CONFIG_NUMA_EMU
 void __cpuinit numa_add_cpu(int cpu)
 {
         cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
@@ -776,34 +786,115 @@ void __cpuinit numa_remove_cpu(int cpu)
 {
         cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
+#else
+void __cpuinit numa_add_cpu(int cpu)
+{
+        unsigned long addr;
+        u16 apicid;
+        int physnid;
+        int nid = NUMA_NO_NODE;
+
+        apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+        if (apicid != BAD_APICID)
+                nid = apicid_to_node[apicid];
+        if (nid == NUMA_NO_NODE)
+                nid = early_cpu_to_node(cpu);
+        BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+
+        /*
+         * Use the starting address of the emulated node to find which physical
+         * node it is allocated on.
+         */
+        addr = node_start_pfn(nid) << PAGE_SHIFT;
+        for (physnid = 0; physnid < MAX_NUMNODES; physnid++)
+                if (addr >= physnodes[physnid].start &&
+                    addr < physnodes[physnid].end)
+                        break;
+
+        /*
+         * Map the cpu to each emulated node that is allocated on the physical
+         * node of the cpu's apic id.
+         */
+        for_each_online_node(nid) {
+                addr = node_start_pfn(nid) << PAGE_SHIFT;
+                if (addr >= physnodes[physnid].start &&
+                    addr < physnodes[physnid].end)
+                        cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+        }
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+        int i;
+
+        for_each_online_node(i)
+                cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
+}
+#endif /* !CONFIG_NUMA_EMU */
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
+static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+{
+        int node = early_cpu_to_node(cpu);
+        struct cpumask *mask;
+        char buf[64];
+
+        mask = node_to_cpumask_map[node];
+        if (!mask) {
+                pr_err("node_to_cpumask_map[%i] NULL\n", node);
+                dump_stack();
+                return NULL;
+        }
+
+        cpulist_scnprintf(buf, sizeof(buf), mask);
+        printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+                enable ? "numa_add_cpu" : "numa_remove_cpu",
+                cpu, node, buf);
+        return mask;
+}
 
 /*
  * --------- debug versions of the numa functions ---------
  */
+#ifndef CONFIG_NUMA_EMU
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
-        int node = early_cpu_to_node(cpu);
         struct cpumask *mask;
-        char buf[64];
 
-        mask = node_to_cpumask_map[node];
-        if (mask == NULL) {
-                printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
-                dump_stack();
+        mask = debug_cpumask_set_cpu(cpu, enable);
+        if (!mask)
                 return;
-        }
 
         if (enable)
                 cpumask_set_cpu(cpu, mask);
         else
                 cpumask_clear_cpu(cpu, mask);
+}
+#else
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+        int node = early_cpu_to_node(cpu);
+        struct cpumask *mask;
+        int i;
 
-        cpulist_scnprintf(buf, sizeof(buf), mask);
-        printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-                enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
+        for_each_online_node(i) {
+                unsigned long addr;
+
+                addr = node_start_pfn(i) << PAGE_SHIFT;
+                if (addr < physnodes[node].start ||
+                                        addr >= physnodes[node].end)
+                        continue;
+                mask = debug_cpumask_set_cpu(cpu, enable);
+                if (!mask)
+                        return;
+
+                if (enable)
+                        cpumask_set_cpu(cpu, mask);
+                else
+                        cpumask_clear_cpu(cpu, mask);
+        }
 }
+#endif /* CONFIG_NUMA_EMU */
 
 void __cpuinit numa_add_cpu(int cpu)
 {
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 532e7933d606..8b830ca14ac4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/percpu.h>
 #include <linux/gfp.h>
+#include <linux/pci.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -255,13 +256,16 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
                                    unsigned long pfn)
 {
         pgprot_t forbidden = __pgprot(0);
+        pgprot_t required = __pgprot(0);
 
         /*
          * The BIOS area between 640k and 1Mb needs to be executable for
          * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
          */
-        if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
+#ifdef CONFIG_PCI_BIOS
+        if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
                 pgprot_val(forbidden) |= _PAGE_NX;
+#endif
 
         /*
          * The kernel text needs to be executable for obvious reasons
@@ -278,6 +282,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
         if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
                    __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
                 pgprot_val(forbidden) |= _PAGE_RW;
+        /*
+         * .data and .bss should always be writable.
+         */
+        if (within(address, (unsigned long)_sdata, (unsigned long)_edata) ||
+            within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop))
+                pgprot_val(required) |= _PAGE_RW;
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
         /*
@@ -317,6 +327,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 #endif
 
         prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
+        prot = __pgprot(pgprot_val(prot) | pgprot_val(required));
 
         return prot;
 }
@@ -393,7 +404,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 {
         unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
         pte_t new_pte, old_pte, *tmp;
-        pgprot_t old_prot, new_prot;
+        pgprot_t old_prot, new_prot, req_prot;
         int i, do_split = 1;
         unsigned int level;
 
@@ -438,10 +449,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
          * We are safe now. Check whether the new pgprot is the same:
          */
         old_pte = *kpte;
-        old_prot = new_prot = pte_pgprot(old_pte);
+        old_prot = new_prot = req_prot = pte_pgprot(old_pte);
 
-        pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
-        pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
+        pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
+        pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
 
         /*
          * old_pte points to the large page base address. So we need
@@ -450,17 +461,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
         pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
         cpa->pfn = pfn;
 
-        new_prot = static_protections(new_prot, address, pfn);
+        new_prot = static_protections(req_prot, address, pfn);
 
         /*
          * We need to check the full range, whether
          * static_protection() requires a different pgprot for one of
          * the pages in the range we try to preserve:
          */
-        addr = address + PAGE_SIZE;
-        pfn++;
-        for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) {
-                pgprot_t chk_prot = static_protections(new_prot, addr, pfn);
+        addr = address & pmask;
+        pfn = pte_pfn(old_pte);
+        for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
+                pgprot_t chk_prot = static_protections(req_prot, addr, pfn);
 
                 if (pgprot_val(chk_prot) != pgprot_val(new_prot))
                         goto out_unlock;
@@ -483,7 +494,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
          * that we limited the number of possible pages already to
          * the number of pages in the large page.
          */
-        if (address == (nextpage_addr - psize) && cpa->numpages == numpages) {
+        if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) {
                 /*
                  * The address is aligned and the number of pages
                  * covers the full page.
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index a3250aa34086..410531d3c292 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -41,7 +41,7 @@ void __init x86_report_nx(void)
 {
         if (!cpu_has_nx) {
                 printk(KERN_NOTICE "Notice: NX (Execute Disable) protection "
-                       "missing in CPU or disabled in BIOS!\n");
+                       "missing in CPU!\n");
         } else {
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
                 if (disable_nx) {
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index a17dffd136c1..f16434568a51 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -92,6 +92,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity)
         /* mark this node as "seen" in node bitmap */
         BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo);
 
+        /* don't need to check apic_id here, because it is always 8 bits */
         apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo;
 
         printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n",
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index a35cb9d8b060..603d285d1daa 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -134,6 +134,10 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
         }
 
         apic_id = pa->apic_id;
+        if (apic_id >= MAX_LOCAL_APIC) {
+                printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+                return;
+        }
         apicid_to_node[apic_id] = node;
         node_set(node, cpu_nodes_parsed);
         acpi_numa = 1;
@@ -168,6 +172,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
                 apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
         else
                 apic_id = pa->apic_id;
+
+        if (apic_id >= MAX_LOCAL_APIC) {
+                printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+                return;
+        }
+
         apicid_to_node[apic_id] = node;
         node_set(node, cpu_nodes_parsed);
         acpi_numa = 1;
@@ -339,18 +349,19 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 
 void __init acpi_numa_arch_fixup(void) {}
 
-int __init acpi_get_nodes(struct bootnode *physnodes)
+#ifdef CONFIG_NUMA_EMU
+void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+                                unsigned long end)
 {
         int i;
-        int ret = 0;
 
         for_each_node_mask(i, nodes_parsed) {
-                physnodes[ret].start = nodes[i].start;
-                physnodes[ret].end = nodes[i].end;
-                ret++;
+                cutoff_node(i, start, end);
+                physnodes[i].start = nodes[i].start;
+                physnodes[i].end = nodes[i].end;
         }
-        return ret;
 }
+#endif /* CONFIG_NUMA_EMU */
 
 /* Use the information discovered above to actually set up the nodes. */
 int __init acpi_scan_nodes(unsigned long start, unsigned long end)
@@ -495,8 +506,6 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 {
         int i, j;
 
-        printk(KERN_INFO "Faking PXM affinity for fake nodes on real "
-                         "topology.\n");
         for (i = 0; i < num_nodes; i++) {
                 int nid, pxm;
 
@@ -516,6 +525,17 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
                             fake_apicid_to_node[j] == NUMA_NO_NODE)
                                 fake_apicid_to_node[j] = i;
         }
+
+        /*
+         * If there are apicid-to-node mappings for physical nodes that do not
+         * have a corresponding emulated node, it should default to a guaranteed
+         * value.
+         */
+        for (i = 0; i < MAX_LOCAL_APIC; i++)
+                if (apicid_to_node[i] != NUMA_NO_NODE &&
+                    fake_apicid_to_node[i] == NUMA_NO_NODE)
+                        fake_apicid_to_node[i] = 0;
+
         for (i = 0; i < num_nodes; i++)
                 __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
         memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 2d49d4e19a36..72cbec14d783 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
         if (!user_mode_vm(regs)) {
                 unsigned long stack = kernel_stack_pointer(regs);
                 if (depth)
-                        dump_trace(NULL, regs, (unsigned long *)stack, 0,
+                        dump_trace(NULL, regs, (unsigned long *)stack,
                                    &backtrace_ops, &depth);
                 return;
         }
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 4e8baad36d37..e2b7b0c06cdf 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -65,7 +65,6 @@ static int profile_exceptions_notify(struct notifier_block *self,
 
         switch (val) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 if (ctr_running)
                         model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
                 else if (!nmi_enabled)
@@ -143,7 +142,7 @@ static inline int has_mux(void)
 
 inline int op_x86_phys_to_virt(int phys)
 {
-        return __get_cpu_var(switch_index) + phys;
+        return __this_cpu_read(switch_index) + phys;
 }
 
 inline int op_x86_virt_to_phys(int virt)
@@ -361,7 +360,7 @@ static void nmi_cpu_setup(void *dummy)
 static struct notifier_block profile_exceptions_nb = {
         .notifier_call = profile_exceptions_notify,
         .next = NULL,
-        .priority = 2
+        .priority = NMI_LOCAL_LOW_PRIOR,
 };
 
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
@@ -732,6 +731,9 @@ int __init op_nmi_init(struct oprofile_operations *ops)
                 case 0x14:
                         cpu_type = "x86-64/family14h";
                         break;
+                case 0x15:
+                        cpu_type = "x86-64/family15h";
+                        break;
                 default:
                         return -ENODEV;
                 }
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index e3ecb71b5790..720bf5a53c51 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -38,7 +38,7 @@ static int profile_timer_exceptions_notify(struct notifier_block *self,
 static struct notifier_block profile_timer_exceptions_nb = {
         .notifier_call = profile_timer_exceptions_notify,
         .next = NULL,
-        .priority = 0
+        .priority = NMI_LOW_PRIOR,
 };
 
 static int timer_start(void)
@@ -58,9 +58,6 @@ static void timer_stop(void)
 
 int __init op_nmi_timer_init(struct oprofile_operations *ops)
 {
-        if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0))
-                return -ENODEV;
-
         ops->start = timer_start;
         ops->stop = timer_stop;
         ops->cpu_type = "timer";
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 7d90d47655ba..c3b8e24f2b16 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -29,11 +29,12 @@
 #include "op_x86_model.h"
 #include "op_counter.h"
 
-#define NUM_COUNTERS 4
+#define NUM_COUNTERS            4
+#define NUM_COUNTERS_F15H       6
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
-#define NUM_VIRT_COUNTERS 32
+#define NUM_VIRT_COUNTERS       32
 #else
-#define NUM_VIRT_COUNTERS NUM_COUNTERS
+#define NUM_VIRT_COUNTERS       0
 #endif
 
 #define OP_EVENT_MASK                   0x0FFF
@@ -41,7 +42,8 @@
 
 #define MSR_AMD_EVENTSEL_RESERVED       ((0xFFFFFCF0ULL<<32)|(1ULL<<21))
 
-static unsigned long reset_value[NUM_VIRT_COUNTERS];
+static int num_counters;
+static unsigned long reset_value[OP_MAX_COUNTER];
 
 #define IBS_FETCH_SIZE                  6
 #define IBS_OP_SIZE                     12
@@ -387,7 +389,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
         int i;
 
         /* enable active counters */
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 int virt = op_x86_phys_to_virt(i);
                 if (!reset_value[virt])
                         continue;
@@ -406,7 +408,7 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
 {
         int i;
 
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 if (!msrs->counters[i].addr)
                         continue;
                 release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
@@ -418,7 +420,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
 {
         int i;
 
-        for (i = 0; i < NUM_COUNTERS; i++) {
+        for (i = 0; i < num_counters; i++) {
                 if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
                         goto fail;
                 if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) {
@@ -426,8 +428,13 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
                         goto fail;
                 }
                 /* both registers must be reserved */
-                msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
-                msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+                if (num_counters == NUM_COUNTERS_F15H) {
+                        msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
+                        msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
+                } else {
+                        msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+                        msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
+                }
                 continue;
         fail:
                 if (!counter_config[i].enabled)
@@ -447,7 +454,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
         int i;
 
         /* setup reset_value */
-        for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
+        for (i = 0; i < OP_MAX_COUNTER; ++i) {
                 if (counter_config[i].enabled
                     && msrs->counters[op_x86_virt_to_phys(i)].addr)
                         reset_value[i] = counter_config[i].count;
@@ -456,7 +463,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
         }
 
         /* clear all counters */
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 if (!msrs->controls[i].addr)
                         continue;
                 rdmsrl(msrs->controls[i].addr, val);
@@ -472,7 +479,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
         }
 
         /* enable active counters */
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 int virt = op_x86_phys_to_virt(i);
                 if (!reset_value[virt])
                         continue;
@@ -503,7 +510,7 @@ static int op_amd_check_ctrs(struct pt_regs * const regs,
         u64 val;
         int i;
 
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 int virt = op_x86_phys_to_virt(i);
                 if (!reset_value[virt])
                         continue;
@@ -526,7 +533,7 @@ static void op_amd_start(struct op_msrs const * const msrs)
         u64 val;
         int i;
 
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 if (!reset_value[op_x86_phys_to_virt(i)])
                         continue;
                 rdmsrl(msrs->controls[i].addr, val);
@@ -546,7 +553,7 @@ static void op_amd_stop(struct op_msrs const * const msrs)
          * Subtle: stop on all counters to avoid race with setting our
          * pm callback
          */
-        for (i = 0; i < NUM_COUNTERS; ++i) {
+        for (i = 0; i < num_counters; ++i) {
                 if (!reset_value[op_x86_phys_to_virt(i)])
                         continue;
                 rdmsrl(msrs->controls[i].addr, val);
@@ -603,6 +610,7 @@ static int force_ibs_eilvt_setup(void)
                 ret = setup_ibs_ctl(i);
                 if (ret)
                         return ret;
+                pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
                 return 0;
         }
 
@@ -706,18 +714,29 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
         return 0;
 }
 
+struct op_x86_model_spec op_amd_spec;
+
 static int op_amd_init(struct oprofile_operations *ops)
 {
         init_ibs();
         create_arch_files = ops->create_files;
         ops->create_files = setup_ibs_files;
+
+        if (boot_cpu_data.x86 == 0x15) {
+                num_counters = NUM_COUNTERS_F15H;
+        } else {
+                num_counters = NUM_COUNTERS;
+        }
+
+        op_amd_spec.num_counters = num_counters;
+        op_amd_spec.num_controls = num_counters;
+        op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS);
+
         return 0;
 }
 
 struct op_x86_model_spec op_amd_spec = {
-        .num_counters           = NUM_COUNTERS,
-        .num_controls           = NUM_COUNTERS,
-        .num_virt_counters      = NUM_VIRT_COUNTERS,
+        /* num_counters/num_controls filled in at runtime */
         .reserved               = MSR_AMD_EVENTSEL_RESERVED,
         .event_mask             = OP_EVENT_MASK,
         .init                   = op_amd_init,
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 182558dd5515..9fadec074142 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -11,7 +11,7 @@
 #include <linux/oprofile.h>
 #include <linux/smp.h>
 #include <linux/ptrace.h>
-#include <linux/nmi.h>
+#include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/fixmap.h>
 #include <asm/apic.h>
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index d769cda54082..94b745045e45 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -95,8 +95,8 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
                  * counter width:
                  */
                 if (!(eax.split.version_id == 0 &&
-                        current_cpu_data.x86 == 6 &&
-                                current_cpu_data.x86_model == 15)) {
+                        __this_cpu_read(cpu_info.x86) == 6 &&
+                                __this_cpu_read(cpu_info.x86_model) == 15)) {
 
                         if (counter_width < eax.split.bit_width)
                                 counter_width = eax.split.bit_width;
@@ -235,8 +235,8 @@ static void arch_perfmon_setup_counters(void)
         eax.full = cpuid_eax(0xa);
 
         /* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
-        if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
-                current_cpu_data.x86_model == 15) {
+        if (eax.split.version_id == 0 && __this_cpu_read(cpu_info.x86) == 6 &&
+                __this_cpu_read(cpu_info.x86_model) == 15) {
                 eax.split.version_id = 2;
                 eax.split.num_counters = 2;
                 eax.split.bit_width = 40;
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index effd96e33f16..6b8759f7634e 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_PCI_OLPC)		+= olpc.o
 obj-$(CONFIG_PCI_XEN)           += xen.o
 
 obj-y                           += fixup.o
+obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)              += acpi.o
 obj-y                           += legacy.o irq.o
 
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index fc1e8fe07e5c..e27dffbbb1a7 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -4,6 +4,7 @@
 #include <linux/cpu.h>
 #include <linux/range.h>
 
+#include <asm/amd_nb.h>
 #include <asm/pci_x86.h>
 
 #include <asm/pci-direct.h>
@@ -378,6 +379,34 @@ static struct notifier_block __cpuinitdata amd_cpu_notifier = {
         .notifier_call  = amd_cpu_notify,
 };
 
+static void __init pci_enable_pci_io_ecs(void)
+{
+#ifdef CONFIG_AMD_NB
+        unsigned int i, n;
+
+        for (n = i = 0; !n && amd_nb_bus_dev_ranges[i].dev_limit; ++i) {
+                u8 bus = amd_nb_bus_dev_ranges[i].bus;
+                u8 slot = amd_nb_bus_dev_ranges[i].dev_base;
+                u8 limit = amd_nb_bus_dev_ranges[i].dev_limit;
+
+                for (; slot < limit; ++slot) {
+                        u32 val = read_pci_config(bus, slot, 3, 0);
+
+                        if (!early_is_amd_nb(val))
+                                continue;
+
+                        val = read_pci_config(bus, slot, 3, 0x8c);
+                        if (!(val & (ENABLE_CF8_EXT_CFG >> 32))) {
+                                val |= ENABLE_CF8_EXT_CFG >> 32;
+                                write_pci_config(bus, slot, 3, 0x8c, val);
+                        }
+                        ++n;
+                }
+        }
+        pr_info("Extended Config Space enabled on %u nodes\n", n);
+#endif
+}
+
 static int __init pci_io_ecs_init(void)
 {
         int cpu;
@@ -386,6 +415,10 @@ static int __init pci_io_ecs_init(void)
         if (boot_cpu_data.x86 < 0x10)
                 return 0;
 
+        /* Try the PCI method first. */
+        if (early_pci_allowed())
+                pci_enable_pci_io_ecs();
+
         register_cpu_notifier(&amd_cpu_notifier);
         for_each_online_cpu(cpu)
                 amd_cpu_notify(&amd_cpu_notifier, (unsigned long)CPU_ONLINE,
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
new file mode 100644
index 000000000000..85b68ef5e809
--- /dev/null
+++ b/arch/x86/pci/ce4100.c
@@ -0,0 +1,315 @@
+/*
+ *  GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2010 Intel Corporation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *  The full GNU General Public License is included in this distribution
+ *  in the file called LICENSE.GPL.
+ *
+ *  Contact Information:
+ *    Intel Corporation
+ *    2200 Mission College Blvd.
+ *    Santa Clara, CA  97052
+ *
+ * This provides access methods for PCI registers that mis-behave on
+ * the CE4100. Each register can be assigned a private init, read and
+ * write routine. The exception to this is the bridge device.  The
+ * bridge device is the only device on bus zero (0) that requires any
+ * fixup so it is a special case ATM
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+
+#include <asm/pci_x86.h>
+
+struct sim_reg {
+        u32 value;
+        u32 mask;
+};
+
+struct sim_dev_reg {
+        int dev_func;
+        int reg;
+        void (*init)(struct sim_dev_reg *reg);
+        void (*read)(struct sim_dev_reg *reg, u32 *value);
+        void (*write)(struct sim_dev_reg *reg, u32 value);
+        struct sim_reg sim_reg;
+};
+
+struct sim_reg_op {
+        void (*init)(struct sim_dev_reg *reg);
+        void (*read)(struct sim_dev_reg *reg, u32 value);
+        void (*write)(struct sim_dev_reg *reg, u32 value);
+};
+
+#define MB (1024 * 1024)
+#define KB (1024)
+#define SIZE_TO_MASK(size) (~(size - 1))
+
+#define DEFINE_REG(device, func, offset, size, init_op, read_op, write_op)\
+{ PCI_DEVFN(device, func), offset, init_op, read_op, write_op,\
+        {0, SIZE_TO_MASK(size)} },
+
+static void reg_init(struct sim_dev_reg *reg)
+{
+        pci_direct_conf1.read(0, 1, reg->dev_func, reg->reg, 4,
+                              &reg->sim_reg.value);
+}
+
+static void reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&pci_config_lock, flags);
+        *value = reg->sim_reg.value;
+        raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
+static void reg_write(struct sim_dev_reg *reg, u32 value)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&pci_config_lock, flags);
+        reg->sim_reg.value = (value & reg->sim_reg.mask) |
+                (reg->sim_reg.value & ~reg->sim_reg.mask);
+        raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
+static void sata_reg_init(struct sim_dev_reg *reg)
+{
+        pci_direct_conf1.read(0, 1, PCI_DEVFN(14, 0), 0x10, 4,
+                              &reg->sim_reg.value);
+        reg->sim_reg.value += 0x400;
+}
+
+static void ehci_reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+        reg_read(reg, value);
+        if (*value != reg->sim_reg.mask)
+                *value |= 0x100;
+}
+
+void sata_revid_init(struct sim_dev_reg *reg)
+{
+        reg->sim_reg.value = 0x01060100;
+        reg->sim_reg.mask = 0;
+}
+
+static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
+{
+        reg_read(reg, value);
+}
+
+static struct sim_dev_reg bus1_fixups[] = {
+        DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(2, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(3, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(4, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(4, 1, 0x10, (128*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(6, 0, 0x10, (512*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(6, 1, 0x10, (512*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(6, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(8, 0, 0x10, (1*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(8, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(8, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(9, 0, 0x10 , (1*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(9, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(10, 0, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(10, 0, 0x14, (256*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 0, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 0, 0x14, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 1, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 2, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 2, 0x14, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 2, 0x18, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 3, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 3, 0x14, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 4, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
+        DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
+        DEFINE_REG(13, 0, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+        DEFINE_REG(13, 1, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x8,  0, sata_revid_init, sata_revid_read, 0)
+        DEFINE_REG(14, 0, 0x10, 0, reg_init, reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x14, 0, reg_init, reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x18, 0, reg_init, reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x1C, 0, reg_init, reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x20, 0, reg_init, reg_read, reg_write)
+        DEFINE_REG(14, 0, 0x24, (0x200), sata_reg_init, reg_read, reg_write)
+        DEFINE_REG(15, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(15, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+        DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+        DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+};
+
+static void __init init_sim_regs(void)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+                if (bus1_fixups[i].init)
+                        bus1_fixups[i].init(&bus1_fixups[i]);
+        }
+}
+
+static inline void extract_bytes(u32 *value, int reg, int len)
+{
+        uint32_t mask;
+
+        *value >>= ((reg & 3) * 8);
+        mask = 0xFFFFFFFF >> ((4 - len) * 8);
+        *value &= mask;
+}
+
+int bridge_read(unsigned int devfn, int reg, int len, u32 *value)
+{
+        u32 av_bridge_base, av_bridge_limit;
+        int retval = 0;
+
+        switch (reg) {
+        /* Make BARs appear to not request any memory. */
+        case PCI_BASE_ADDRESS_0:
+        case PCI_BASE_ADDRESS_0 + 1:
+        case PCI_BASE_ADDRESS_0 + 2:
+        case PCI_BASE_ADDRESS_0 + 3:
+                *value = 0;
+                break;
+
+                /* Since subordinate bus number register is hardwired
+                 * to zero and read only, so do the simulation.
+                 */
+        case PCI_PRIMARY_BUS:
+                if (len == 4)
+                        *value = 0x00010100;
+                break;
+
+        case PCI_SUBORDINATE_BUS:
+                *value = 1;
+                break;
+
+        case PCI_MEMORY_BASE:
+        case PCI_MEMORY_LIMIT:
+                /* Get the A/V bridge base address. */
+                pci_direct_conf1.read(0, 0, devfn,
+                                PCI_BASE_ADDRESS_0, 4, &av_bridge_base);
+
+                av_bridge_limit = av_bridge_base + (512*MB - 1);
+                av_bridge_limit >>= 16;
+                av_bridge_limit &= 0xFFF0;
+
+                av_bridge_base >>= 16;
+                av_bridge_base &= 0xFFF0;
+
+                if (reg == PCI_MEMORY_LIMIT)
+                        *value = av_bridge_limit;
+                else if (len == 2)
+                        *value = av_bridge_base;
+                else
+                        *value = (av_bridge_limit << 16) | av_bridge_base;
+                break;
+                /* Make prefetchable memory limit smaller than prefetchable
+                 * memory base, so not claim prefetchable memory space.
+                 */
+        case PCI_PREF_MEMORY_BASE:
+                *value = 0xFFF0;
+                break;
+        case PCI_PREF_MEMORY_LIMIT:
+                *value = 0x0;
+                break;
+                /* Make IO limit smaller than IO base, so not claim IO space. */
+        case PCI_IO_BASE:
+                *value = 0xF0;
+                break;
+        case PCI_IO_LIMIT:
+                *value = 0;
+                break;
+        default:
+                retval = 1;
+        }
+        return retval;
+}
+
+static int ce4100_conf_read(unsigned int seg, unsigned int bus,
+                            unsigned int devfn, int reg, int len, u32 *value)
+{
+        int i, retval = 1;
+
+        if (bus == 1) {
+                for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+                        if (bus1_fixups[i].dev_func == devfn &&
+                            bus1_fixups[i].reg == (reg & ~3) &&
+                            bus1_fixups[i].read) {
+                                bus1_fixups[i].read(&(bus1_fixups[i]),
+                                                    value);
+                                extract_bytes(value, reg, len);
+                                return 0;
+                        }
+                }
+        }
+
+        if (bus == 0 && (PCI_DEVFN(1, 0) == devfn) &&
+            !bridge_read(devfn, reg, len, value))
+                return 0;
+
+        return pci_direct_conf1.read(seg, bus, devfn, reg, len, value);
+}
+
+static int ce4100_conf_write(unsigned int seg, unsigned int bus,
+                             unsigned int devfn, int reg, int len, u32 value)
+{
+        int i;
+
+        if (bus == 1) {
+                for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+                        if (bus1_fixups[i].dev_func == devfn &&
+                            bus1_fixups[i].reg == (reg & ~3) &&
+                            bus1_fixups[i].write) {
+                                bus1_fixups[i].write(&(bus1_fixups[i]),
+                                                     value);
+                                return 0;
+                        }
+                }
+        }
+
+        /* Discard writes to A/V bridge BAR. */
+        if (bus == 0 && PCI_DEVFN(1, 0) == devfn &&
+            ((reg & ~3) == PCI_BASE_ADDRESS_0))
+                return 0;
+
+        return pci_direct_conf1.write(seg, bus, devfn, reg, len, value);
+}
+
+struct pci_raw_ops ce4100_pci_conf = {
+        .read = ce4100_conf_read,
+        .write = ce4100_conf_write,
+};
+
+static int __init ce4100_pci_init(void)
+{
+        init_sim_regs();
+        raw_pci_ops = &ce4100_pci_conf;
+        return 0;
+}
+subsys_initcall(ce4100_pci_init);
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 2492d165096a..a5f7d0d63de0 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -9,6 +9,7 @@
 #include <linux/uaccess.h>
 #include <asm/pci_x86.h>
 #include <asm/pci-functions.h>
+#include <asm/cacheflush.h>
 
 /* BIOS32 signature: "_32_" */
 #define BIOS32_SIGNATURE        (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
@@ -25,6 +26,27 @@
 #define PCIBIOS_HW_TYPE1_SPEC           0x10
 #define PCIBIOS_HW_TYPE2_SPEC           0x20
 
+int pcibios_enabled;
+
+/* According to the BIOS specification at:
+ * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
+ * restrict the x zone to some pages and make it ro. But this may be
+ * broken on some bios, complex to handle with static_protections.
+ * We could make the 0xe0000-0x100000 range rox, but this can break
+ * some ISA mapping.
+ *
+ * So we let's an rw and x hole when pcibios is used. This shouldn't
+ * happen for modern system with mmconfig, and if you don't want it
+ * you could disable pcibios...
+ */
+static inline void set_bios_x(void)
+{
+        pcibios_enabled = 1;
+        set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT);
+        if (__supported_pte_mask & _PAGE_NX)
+                printk(KERN_INFO "PCI : PCI BIOS aera is rw and x. Use pci=nobios if you want it NX.\n");
+}
+
 /*
  * This is the standard structure used to identify the entry point
  * to the BIOS32 Service Directory, as documented in
@@ -332,6 +354,7 @@ static struct pci_raw_ops * __devinit pci_find_bios(void)
                         DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n",
                                         bios32_entry);
                         bios32_indirect.address = bios32_entry + PAGE_OFFSET;
+                        set_bios_x();
                         if (check_pcibios())
                                 return &pci_bios_access;
                 }
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index 7bf70b812fa2..021eee91c056 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -1,5 +1,7 @@
 # Platform specific code goes here
+obj-y   += ce4100/
 obj-y   += efi/
+obj-y   += iris/
 obj-y   += mrst/
 obj-y   += olpc/
 obj-y   += scx200/
diff --git a/arch/x86/platform/ce4100/Makefile b/arch/x86/platform/ce4100/Makefile
new file mode 100644
index 000000000000..91fc92971d94
--- /dev/null
+++ b/arch/x86/platform/ce4100/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
new file mode 100644
index 000000000000..d2c0d51a7178
--- /dev/null
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -0,0 +1,132 @@
+/*
+ * Intel CE4100  platform specific setup code
+ *
+ * (C) Copyright 2010 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/serial_reg.h>
+#include <linux/serial_8250.h>
+
+#include <asm/setup.h>
+#include <asm/io.h>
+
+static int ce4100_i8042_detect(void)
+{
+        return 0;
+}
+
+static void __init sdv_find_smp_config(void)
+{
+}
+
+#ifdef CONFIG_SERIAL_8250
+
+
+static unsigned int mem_serial_in(struct uart_port *p, int offset)
+{
+        offset = offset << p->regshift;
+        return readl(p->membase + offset);
+}
+
+/*
+ * The UART Tx interrupts are not set under some conditions and therefore serial
+ * transmission hangs. This is a silicon issue and has not been root caused. The
+ * workaround for this silicon issue checks UART_LSR_THRE bit and UART_LSR_TEMT
+ * bit of LSR register in interrupt handler to see whether at least one of these
+ * two bits is set, if so then process the transmit request. If this workaround
+ * is not applied, then the serial transmission may hang. This workaround is for
+ * errata number 9 in Errata - B step.
+*/
+
+static unsigned int ce4100_mem_serial_in(struct uart_port *p, int offset)
+{
+        unsigned int ret, ier, lsr;
+
+        if (offset == UART_IIR) {
+                offset = offset << p->regshift;
+                ret = readl(p->membase + offset);
+                if (ret & UART_IIR_NO_INT) {
+                        /* see if the TX interrupt should have really set */
+                        ier = mem_serial_in(p, UART_IER);
+                        /* see if the UART's XMIT interrupt is enabled */
+                        if (ier & UART_IER_THRI) {
+                                lsr = mem_serial_in(p, UART_LSR);
+                                /* now check to see if the UART should be
+                                   generating an interrupt (but isn't) */
+                                if (lsr & (UART_LSR_THRE | UART_LSR_TEMT))
+                                        ret &= ~UART_IIR_NO_INT;
+                        }
+                }
+        } else
+                ret =  mem_serial_in(p, offset);
+        return ret;
+}
+
+static void ce4100_mem_serial_out(struct uart_port *p, int offset, int value)
+{
+        offset = offset << p->regshift;
+        writel(value, p->membase + offset);
+}
+
+static void ce4100_serial_fixup(int port, struct uart_port *up,
+        unsigned short *capabilites)
+{
+#ifdef CONFIG_EARLY_PRINTK
+        /*
+         * Over ride the legacy port configuration that comes from
+         * asm/serial.h. Using the ioport driver then switching to the
+         * PCI memmaped driver hangs the IOAPIC
+         */
+        if (up->iotype !=  UPIO_MEM32) {
+                up->uartclk  = 14745600;
+                up->mapbase = 0xdffe0200;
+                set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
+                                up->mapbase & PAGE_MASK);
+                up->membase =
+                        (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
+                up->membase += up->mapbase & ~PAGE_MASK;
+                up->iotype   = UPIO_MEM32;
+                up->regshift = 2;
+        }
+#endif
+        up->iobase = 0;
+        up->serial_in = ce4100_mem_serial_in;
+        up->serial_out = ce4100_mem_serial_out;
+
+        *capabilites |= (1 << 12);
+}
+
+static __init void sdv_serial_fixup(void)
+{
+        serial8250_set_isa_configurator(ce4100_serial_fixup);
+}
+
+#else
+static inline void sdv_serial_fixup(void);
+#endif
+
+static void __init sdv_arch_setup(void)
+{
+        sdv_serial_fixup();
+}
+
+/*
+ * CE4100 specific x86_init function overrides and early setup
+ * calls.
+ */
+void __init x86_ce4100_early_setup(void)
+{
+        x86_init.oem.arch_setup = sdv_arch_setup;
+        x86_platform.i8042_detect = ce4100_i8042_detect;
+        x86_init.resources.probe_roms = x86_init_noop;
+        x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+        x86_init.mpparse.find_smp_config = sdv_find_smp_config;
+}
diff --git a/arch/x86/platform/iris/Makefile b/arch/x86/platform/iris/Makefile
new file mode 100644
index 000000000000..db921983a102
--- /dev/null
+++ b/arch/x86/platform/iris/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_X86_32_IRIS)               += iris.o
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
new file mode 100644
index 000000000000..1ba7f5ed8c9b
--- /dev/null
+++ b/arch/x86/platform/iris/iris.c
@@ -0,0 +1,91 @@
+/*
+ * Eurobraille/Iris power off support.
+ *
+ * Eurobraille's Iris machine is a PC with no APM or ACPI support.
+ * It is shutdown by a special I/O sequence which this module provides.
+ *
+ *  Copyright (C) Shérab <Sebastien.Hinderer@ens-lyon.org>
+ *
+ * This program is free software ; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation ; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY ; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with the program ; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/moduleparam.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <asm/io.h>
+
+#define IRIS_GIO_BASE           0x340
+#define IRIS_GIO_INPUT          IRIS_GIO_BASE
+#define IRIS_GIO_OUTPUT         (IRIS_GIO_BASE + 1)
+#define IRIS_GIO_PULSE          0x80 /* First byte to send */
+#define IRIS_GIO_REST           0x00 /* Second byte to send */
+#define IRIS_GIO_NODEV          0xff /* Likely not an Iris */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
+MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
+MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
+
+static int force;
+
+module_param(force, bool, 0);
+MODULE_PARM_DESC(force, "Set to one to force poweroff handler installation.");
+
+static void (*old_pm_power_off)(void);
+
+static void iris_power_off(void)
+{
+        outb(IRIS_GIO_PULSE, IRIS_GIO_OUTPUT);
+        msleep(850);
+        outb(IRIS_GIO_REST, IRIS_GIO_OUTPUT);
+}
+
+/*
+ * Before installing the power_off handler, try to make sure the OS is
+ * running on an Iris.  Since Iris does not support DMI, this is done
+ * by reading its input port and seeing whether the read value is
+ * meaningful.
+ */
+static int iris_init(void)
+{
+        unsigned char status;
+        if (force != 1) {
+                printk(KERN_ERR "The force parameter has not been set to 1 so the Iris poweroff handler will not be installed.\n");
+                return -ENODEV;
+        }
+        status = inb(IRIS_GIO_INPUT);
+        if (status == IRIS_GIO_NODEV) {
+                printk(KERN_ERR "This machine does not seem to be an Iris. Power_off handler not installed.\n");
+                return -ENODEV;
+        }
+        old_pm_power_off = pm_power_off;
+        pm_power_off = &iris_power_off;
+        printk(KERN_INFO "Iris power_off handler installed.\n");
+
+        return 0;
+}
+
+static void iris_exit(void)
+{
+        pm_power_off = old_pm_power_off;
+        printk(KERN_INFO "Iris power_off handler uninstalled.\n");
+}
+
+module_init(iris_init);
+module_exit(iris_exit);
diff --git a/arch/x86/platform/mrst/Makefile b/arch/x86/platform/mrst/Makefile
index efbbc552fa95..f61ccdd49341 100644
--- a/arch/x86/platform/mrst/Makefile
+++ b/arch/x86/platform/mrst/Makefile
@@ -1 +1,3 @@
 obj-$(CONFIG_X86_MRST)          += mrst.o
+obj-$(CONFIG_X86_MRST)          += vrtc.o
+obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o
diff --git a/arch/x86/kernel/early_printk_mrst.c b/arch/x86/platform/mrst/early_printk_mrst.c
index 65df603622b2..65df603622b2 100644
--- a/arch/x86/kernel/early_printk_mrst.c
+++ b/arch/x86/platform/mrst/early_printk_mrst.c
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 79ae68154e87..ea6529e93c6f 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -9,9 +9,19 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
+
+#define pr_fmt(fmt) "mrst: " fmt
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sfi.h>
+#include <linux/intel_pmic_gpio.h>
+#include <linux/spi/spi.h>
+#include <linux/i2c.h>
+#include <linux/i2c/pca953x.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/module.h>
 
@@ -23,7 +33,9 @@
 #include <asm/mrst.h>
 #include <asm/io.h>
 #include <asm/i8259.h>
+#include <asm/intel_scu_ipc.h>
 #include <asm/apb_timer.h>
+#include <asm/reboot.h>
 
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
@@ -59,32 +71,6 @@ struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
 EXPORT_SYMBOL_GPL(sfi_mrtc_array);
 int sfi_mrtc_num;
 
-static inline void assign_to_mp_irq(struct mpc_intsrc *m,
-                                    struct mpc_intsrc *mp_irq)
-{
-        memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
-}
-
-static inline int mp_irq_cmp(struct mpc_intsrc *mp_irq,
-                                struct mpc_intsrc *m)
-{
-        return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
-}
-
-static void save_mp_irq(struct mpc_intsrc *m)
-{
-        int i;
-
-        for (i = 0; i < mp_irq_entries; i++) {
-                if (!mp_irq_cmp(&mp_irqs[i], m))
-                        return;
-        }
-
-        assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
-        if (++mp_irq_entries == MAX_IRQ_SOURCES)
-                panic("Max # of irq sources exceeded!!\n");
-}
-
 /* parse all the mtimer info to a static mtimer array */
 static int __init sfi_parse_mtmr(struct sfi_table_header *table)
 {
@@ -102,10 +88,10 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table)
                 memcpy(sfi_mtimer_array, pentry, totallen);
         }
 
-        printk(KERN_INFO "SFI: MTIMER info (num = %d):\n", sfi_mtimer_num);
+        pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num);
         pentry = sfi_mtimer_array;
         for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) {
-                printk(KERN_INFO "timer[%d]: paddr = 0x%08x, freq = %dHz,"
+                pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz,"
                         " irq = %d\n", totallen, (u32)pentry->phys_addr,
                         pentry->freq_hz, pentry->irq);
                         if (!pentry->irq)
@@ -118,7 +104,7 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table)
                         mp_irq.srcbusirq = pentry->irq; /* IRQ */
                         mp_irq.dstapic = MP_APIC_ALL;
                         mp_irq.dstirq = pentry->irq;
-                        save_mp_irq(&mp_irq);
+                        mp_save_irq(&mp_irq);
         }
 
         return 0;
@@ -176,19 +162,19 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
                 memcpy(sfi_mrtc_array, pentry, totallen);
         }
 
-        printk(KERN_INFO "SFI: RTC info (num = %d):\n", sfi_mrtc_num);
+        pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num);
         pentry = sfi_mrtc_array;
         for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
-                printk(KERN_INFO "RTC[%d]: paddr = 0x%08x, irq = %d\n",
+                pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
                         totallen, (u32)pentry->phys_addr, pentry->irq);
                 mp_irq.type = MP_IOAPIC;
                 mp_irq.irqtype = mp_INT;
-                mp_irq.irqflag = 0;
+                mp_irq.irqflag = 0xf;   /* level trigger and active low */
                 mp_irq.srcbus = 0;
                 mp_irq.srcbusirq = pentry->irq; /* IRQ */
                 mp_irq.dstapic = MP_APIC_ALL;
                 mp_irq.dstirq = pentry->irq;
-                save_mp_irq(&mp_irq);
+                mp_save_irq(&mp_irq);
         }
         return 0;
 }
@@ -209,6 +195,7 @@ static unsigned long __init mrst_calibrate_tsc(void)
 
 void __init mrst_time_init(void)
 {
+        sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
         switch (mrst_timer_options) {
         case MRST_TIMER_APBT_ONLY:
                 break;
@@ -224,16 +211,10 @@ void __init mrst_time_init(void)
                 return;
         }
         /* we need at least one APB timer */
-        sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
         pre_init_apic_IRQ0();
         apbt_time_init();
 }
 
-void __init mrst_rtc_init(void)
-{
-        sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
-}
-
 void __cpuinit mrst_arch_setup(void)
 {
         if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
@@ -256,6 +237,17 @@ static int mrst_i8042_detect(void)
         return 0;
 }
 
+/* Reboot and power off are handled by the SCU on a MID device */
+static void mrst_power_off(void)
+{
+        intel_scu_ipc_simple_command(0xf1, 1);
+}
+
+static void mrst_reboot(void)
+{
+        intel_scu_ipc_simple_command(0xf1, 0);
+}
+
 /*
  * Moorestown specific x86_init function overrides and early setup
  * calls.
@@ -281,6 +273,10 @@ void __init x86_mrst_early_setup(void)
 
         legacy_pic = &null_legacy_pic;
 
+        /* Moorestown specific power_off/restart method */
+        pm_power_off = mrst_power_off;
+        machine_ops.emergency_restart  = mrst_reboot;
+
         /* Avoid searching for BIOS MP tables */
         x86_init.mpparse.find_smp_config = x86_init_noop;
         x86_init.mpparse.get_smp_config = x86_init_uint_noop;
@@ -309,3 +305,505 @@ static inline int __init setup_x86_mrst_timer(char *arg)
         return 0;
 }
 __setup("x86_mrst_timer=", setup_x86_mrst_timer);
+
+/*
+ * Parsing GPIO table first, since the DEVS table will need this table
+ * to map the pin name to the actual pin.
+ */
+static struct sfi_gpio_table_entry *gpio_table;
+static int gpio_num_entry;
+
+static int __init sfi_parse_gpio(struct sfi_table_header *table)
+{
+        struct sfi_table_simple *sb;
+        struct sfi_gpio_table_entry *pentry;
+        int num, i;
+
+        if (gpio_table)
+                return 0;
+        sb = (struct sfi_table_simple *)table;
+        num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry);
+        pentry = (struct sfi_gpio_table_entry *)sb->pentry;
+
+        gpio_table = (struct sfi_gpio_table_entry *)
+                                kmalloc(num * sizeof(*pentry), GFP_KERNEL);
+        if (!gpio_table)
+                return -1;
+        memcpy(gpio_table, pentry, num * sizeof(*pentry));
+        gpio_num_entry = num;
+
+        pr_debug("GPIO pin info:\n");
+        for (i = 0; i < num; i++, pentry++)
+                pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s,"
+                " pin = %d\n", i,
+                        pentry->controller_name,
+                        pentry->pin_name,
+                        pentry->pin_no);
+        return 0;
+}
+
+static int get_gpio_by_name(const char *name)
+{
+        struct sfi_gpio_table_entry *pentry = gpio_table;
+        int i;
+
+        if (!pentry)
+                return -1;
+        for (i = 0; i < gpio_num_entry; i++, pentry++) {
+                if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN))
+                        return pentry->pin_no;
+        }
+        return -1;
+}
+
+/*
+ * Here defines the array of devices platform data that IAFW would export
+ * through SFI "DEVS" table, we use name and type to match the device and
+ * its platform data.
+ */
+struct devs_id {
+        char name[SFI_NAME_LEN + 1];
+        u8 type;
+        u8 delay;
+        void *(*get_platform_data)(void *info);
+};
+
+/* the offset for the mapping of global gpio pin to irq */
+#define MRST_IRQ_OFFSET 0x100
+
+static void __init *pmic_gpio_platform_data(void *info)
+{
+        static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
+        int gpio_base = get_gpio_by_name("pmic_gpio_base");
+
+        if (gpio_base == -1)
+                gpio_base = 64;
+        pmic_gpio_pdata.gpio_base = gpio_base;
+        pmic_gpio_pdata.irq_base = gpio_base + MRST_IRQ_OFFSET;
+        pmic_gpio_pdata.gpiointr = 0xffffeff8;
+
+        return &pmic_gpio_pdata;
+}
+
+static void __init *max3111_platform_data(void *info)
+{
+        struct spi_board_info *spi_info = info;
+        int intr = get_gpio_by_name("max3111_int");
+
+        if (intr == -1)
+                return NULL;
+        spi_info->irq = intr + MRST_IRQ_OFFSET;
+        return NULL;
+}
+
+/* we have multiple max7315 on the board ... */
+#define MAX7315_NUM 2
+static void __init *max7315_platform_data(void *info)
+{
+        static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
+        static int nr;
+        struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
+        struct i2c_board_info *i2c_info = info;
+        int gpio_base, intr;
+        char base_pin_name[SFI_NAME_LEN + 1];
+        char intr_pin_name[SFI_NAME_LEN + 1];
+
+        if (nr == MAX7315_NUM) {
+                pr_err("too many max7315s, we only support %d\n",
+                                MAX7315_NUM);
+                return NULL;
+        }
+        /* we have several max7315 on the board, we only need load several
+         * instances of the same pca953x driver to cover them
+         */
+        strcpy(i2c_info->type, "max7315");
+        if (nr++) {
+                sprintf(base_pin_name, "max7315_%d_base", nr);
+                sprintf(intr_pin_name, "max7315_%d_int", nr);
+        } else {
+                strcpy(base_pin_name, "max7315_base");
+                strcpy(intr_pin_name, "max7315_int");
+        }
+
+        gpio_base = get_gpio_by_name(base_pin_name);
+        intr = get_gpio_by_name(intr_pin_name);
+
+        if (gpio_base == -1)
+                return NULL;
+        max7315->gpio_base = gpio_base;
+        if (intr != -1) {
+                i2c_info->irq = intr + MRST_IRQ_OFFSET;
+                max7315->irq_base = gpio_base + MRST_IRQ_OFFSET;
+        } else {
+                i2c_info->irq = -1;
+                max7315->irq_base = -1;
+        }
+        return max7315;
+}
+
+static void __init *emc1403_platform_data(void *info)
+{
+        static short intr2nd_pdata;
+        struct i2c_board_info *i2c_info = info;
+        int intr = get_gpio_by_name("thermal_int");
+        int intr2nd = get_gpio_by_name("thermal_alert");
+
+        if (intr == -1 || intr2nd == -1)
+                return NULL;
+
+        i2c_info->irq = intr + MRST_IRQ_OFFSET;
+        intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
+
+        return &intr2nd_pdata;
+}
+
+static void __init *lis331dl_platform_data(void *info)
+{
+        static short intr2nd_pdata;
+        struct i2c_board_info *i2c_info = info;
+        int intr = get_gpio_by_name("accel_int");
+        int intr2nd = get_gpio_by_name("accel_2");
+
+        if (intr == -1 || intr2nd == -1)
+                return NULL;
+
+        i2c_info->irq = intr + MRST_IRQ_OFFSET;
+        intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
+
+        return &intr2nd_pdata;
+}
+
+static void __init *no_platform_data(void *info)
+{
+        return NULL;
+}
+
+static const struct devs_id __initconst device_ids[] = {
+        {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+        {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
+        {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+        {"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+        {"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
+        {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
+        {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+        {"msic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+        {},
+};
+
+#define MAX_IPCDEVS     24
+static struct platform_device *ipc_devs[MAX_IPCDEVS];
+static int ipc_next_dev;
+
+#define MAX_SCU_SPI     24
+static struct spi_board_info *spi_devs[MAX_SCU_SPI];
+static int spi_next_dev;
+
+#define MAX_SCU_I2C     24
+static struct i2c_board_info *i2c_devs[MAX_SCU_I2C];
+static int i2c_bus[MAX_SCU_I2C];
+static int i2c_next_dev;
+
+static void __init intel_scu_device_register(struct platform_device *pdev)
+{
+        if(ipc_next_dev == MAX_IPCDEVS)
+                pr_err("too many SCU IPC devices");
+        else
+                ipc_devs[ipc_next_dev++] = pdev;
+}
+
+static void __init intel_scu_spi_device_register(struct spi_board_info *sdev)
+{
+        struct spi_board_info *new_dev;
+
+        if (spi_next_dev == MAX_SCU_SPI) {
+                pr_err("too many SCU SPI devices");
+                return;
+        }
+
+        new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+        if (!new_dev) {
+                pr_err("failed to alloc mem for delayed spi dev %s\n",
+                        sdev->modalias);
+                return;
+        }
+        memcpy(new_dev, sdev, sizeof(*sdev));
+
+        spi_devs[spi_next_dev++] = new_dev;
+}
+
+static void __init intel_scu_i2c_device_register(int bus,
+                                                struct i2c_board_info *idev)
+{
+        struct i2c_board_info *new_dev;
+
+        if (i2c_next_dev == MAX_SCU_I2C) {
+                pr_err("too many SCU I2C devices");
+                return;
+        }
+
+        new_dev = kzalloc(sizeof(*idev), GFP_KERNEL);
+        if (!new_dev) {
+                pr_err("failed to alloc mem for delayed i2c dev %s\n",
+                        idev->type);
+                return;
+        }
+        memcpy(new_dev, idev, sizeof(*idev));
+
+        i2c_bus[i2c_next_dev] = bus;
+        i2c_devs[i2c_next_dev++] = new_dev;
+}
+
+/* Called by IPC driver */
+void intel_scu_devices_create(void)
+{
+        int i;
+
+        for (i = 0; i < ipc_next_dev; i++)
+                platform_device_add(ipc_devs[i]);
+
+        for (i = 0; i < spi_next_dev; i++)
+                spi_register_board_info(spi_devs[i], 1);
+
+        for (i = 0; i < i2c_next_dev; i++) {
+                struct i2c_adapter *adapter;
+                struct i2c_client *client;
+
+                adapter = i2c_get_adapter(i2c_bus[i]);
+                if (adapter) {
+                        client = i2c_new_device(adapter, i2c_devs[i]);
+                        if (!client)
+                                pr_err("can't create i2c device %s\n",
+                                        i2c_devs[i]->type);
+                } else
+                        i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
+        }
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_create);
+
+/* Called by IPC driver */
+void intel_scu_devices_destroy(void)
+{
+        int i;
+
+        for (i = 0; i < ipc_next_dev; i++)
+                platform_device_del(ipc_devs[i]);
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_destroy);
+
+static void __init install_irq_resource(struct platform_device *pdev, int irq)
+{
+        /* Single threaded */
+        static struct resource __initdata res = {
+                .name = "IRQ",
+                .flags = IORESOURCE_IRQ,
+        };
+        res.start = irq;
+        platform_device_add_resources(pdev, &res, 1);
+}
+
+static void __init sfi_handle_ipc_dev(struct platform_device *pdev)
+{
+        const struct devs_id *dev = device_ids;
+        void *pdata = NULL;
+
+        while (dev->name[0]) {
+                if (dev->type == SFI_DEV_TYPE_IPC &&
+                        !strncmp(dev->name, pdev->name, SFI_NAME_LEN)) {
+                        pdata = dev->get_platform_data(pdev);
+                        break;
+                }
+                dev++;
+        }
+        pdev->dev.platform_data = pdata;
+        intel_scu_device_register(pdev);
+}
+
+static void __init sfi_handle_spi_dev(struct spi_board_info *spi_info)
+{
+        const struct devs_id *dev = device_ids;
+        void *pdata = NULL;
+
+        while (dev->name[0]) {
+                if (dev->type == SFI_DEV_TYPE_SPI &&
+                                !strncmp(dev->name, spi_info->modalias, SFI_NAME_LEN)) {
+                        pdata = dev->get_platform_data(spi_info);
+                        break;
+                }
+                dev++;
+        }
+        spi_info->platform_data = pdata;
+        if (dev->delay)
+                intel_scu_spi_device_register(spi_info);
+        else
+                spi_register_board_info(spi_info, 1);
+}
+
+static void __init sfi_handle_i2c_dev(int bus, struct i2c_board_info *i2c_info)
+{
+        const struct devs_id *dev = device_ids;
+        void *pdata = NULL;
+
+        while (dev->name[0]) {
+                if (dev->type == SFI_DEV_TYPE_I2C &&
+                        !strncmp(dev->name, i2c_info->type, SFI_NAME_LEN)) {
+                        pdata = dev->get_platform_data(i2c_info);
+                        break;
+                }
+                dev++;
+        }
+        i2c_info->platform_data = pdata;
+
+        if (dev->delay)
+                intel_scu_i2c_device_register(bus, i2c_info);
+        else
+                i2c_register_board_info(bus, i2c_info, 1);
+ }
+
+
+static int __init sfi_parse_devs(struct sfi_table_header *table)
+{
+        struct sfi_table_simple *sb;
+        struct sfi_device_table_entry *pentry;
+        struct spi_board_info spi_info;
+        struct i2c_board_info i2c_info;
+        struct platform_device *pdev;
+        int num, i, bus;
+        int ioapic;
+        struct io_apic_irq_attr irq_attr;
+
+        sb = (struct sfi_table_simple *)table;
+        num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
+        pentry = (struct sfi_device_table_entry *)sb->pentry;
+
+        for (i = 0; i < num; i++, pentry++) {
+                if (pentry->irq != (u8)0xff) { /* native RTE case */
+                        /* these SPI2 devices are not exposed to system as PCI
+                         * devices, but they have separate RTE entry in IOAPIC
+                         * so we have to enable them one by one here
+                         */
+                        ioapic = mp_find_ioapic(pentry->irq);
+                        irq_attr.ioapic = ioapic;
+                        irq_attr.ioapic_pin = pentry->irq;
+                        irq_attr.trigger = 1;
+                        irq_attr.polarity = 1;
+                        io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr);
+                }
+                switch (pentry->type) {
+                case SFI_DEV_TYPE_IPC:
+                        /* ID as IRQ is a hack that will go away */
+                        pdev = platform_device_alloc(pentry->name, pentry->irq);
+                        if (pdev == NULL) {
+                                pr_err("out of memory for SFI platform device '%s'.\n",
+                                                        pentry->name);
+                                continue;
+                        }
+                        install_irq_resource(pdev, pentry->irq);
+                        pr_debug("info[%2d]: IPC bus, name = %16.16s, "
+                                "irq = 0x%2x\n", i, pentry->name, pentry->irq);
+                        sfi_handle_ipc_dev(pdev);
+                        break;
+                case SFI_DEV_TYPE_SPI:
+                        memset(&spi_info, 0, sizeof(spi_info));
+                        strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN);
+                        spi_info.irq = pentry->irq;
+                        spi_info.bus_num = pentry->host_num;
+                        spi_info.chip_select = pentry->addr;
+                        spi_info.max_speed_hz = pentry->max_freq;
+                        pr_debug("info[%2d]: SPI bus = %d, name = %16.16s, "
+                                "irq = 0x%2x, max_freq = %d, cs = %d\n", i,
+                                spi_info.bus_num,
+                                spi_info.modalias,
+                                spi_info.irq,
+                                spi_info.max_speed_hz,
+                                spi_info.chip_select);
+                        sfi_handle_spi_dev(&spi_info);
+                        break;
+                case SFI_DEV_TYPE_I2C:
+                        memset(&i2c_info, 0, sizeof(i2c_info));
+                        bus = pentry->host_num;
+                        strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN);
+                        i2c_info.irq = pentry->irq;
+                        i2c_info.addr = pentry->addr;
+                        pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, "
+                                "irq = 0x%2x, addr = 0x%x\n", i, bus,
+                                i2c_info.type,
+                                i2c_info.irq,
+                                i2c_info.addr);
+                        sfi_handle_i2c_dev(bus, &i2c_info);
+                        break;
+                case SFI_DEV_TYPE_UART:
+                case SFI_DEV_TYPE_HSI:
+                default:
+                        ;
+                }
+        }
+        return 0;
+}
+
+static int __init mrst_platform_init(void)
+{
+        sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio);
+        sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs);
+        return 0;
+}
+arch_initcall(mrst_platform_init);
+
+/*
+ * we will search these buttons in SFI GPIO table (by name)
+ * and register them dynamically. Please add all possible
+ * buttons here, we will shrink them if no GPIO found.
+ */
+static struct gpio_keys_button gpio_button[] = {
+        {KEY_POWER,             -1, 1, "power_btn",     EV_KEY, 0, 3000},
+        {KEY_PROG1,             -1, 1, "prog_btn1",     EV_KEY, 0, 20},
+        {KEY_PROG2,             -1, 1, "prog_btn2",     EV_KEY, 0, 20},
+        {SW_LID,                -1, 1, "lid_switch",    EV_SW,  0, 20},
+        {KEY_VOLUMEUP,          -1, 1, "vol_up",        EV_KEY, 0, 20},
+        {KEY_VOLUMEDOWN,        -1, 1, "vol_down",      EV_KEY, 0, 20},
+        {KEY_CAMERA,            -1, 1, "camera_full",   EV_KEY, 0, 20},
+        {KEY_CAMERA_FOCUS,      -1, 1, "camera_half",   EV_KEY, 0, 20},
+        {SW_KEYPAD_SLIDE,       -1, 1, "MagSw1",        EV_SW,  0, 20},
+        {SW_KEYPAD_SLIDE,       -1, 1, "MagSw2",        EV_SW,  0, 20},
+};
+
+static struct gpio_keys_platform_data mrst_gpio_keys = {
+        .buttons        = gpio_button,
+        .rep            = 1,
+        .nbuttons       = -1, /* will fill it after search */
+};
+
+static struct platform_device pb_device = {
+        .name           = "gpio-keys",
+        .id             = -1,
+        .dev            = {
+                .platform_data  = &mrst_gpio_keys,
+        },
+};
+
+/*
+ * Shrink the non-existent buttons, register the gpio button
+ * device if there is some
+ */
+static int __init pb_keys_init(void)
+{
+        struct gpio_keys_button *gb = gpio_button;
+        int i, num, good = 0;
+
+        num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
+        for (i = 0; i < num; i++) {
+                gb[i].gpio = get_gpio_by_name(gb[i].desc);
+                if (gb[i].gpio == -1)
+                        continue;
+
+                if (i != good)
+                        gb[good] = gb[i];
+                good++;
+        }
+
+        if (good) {
+                mrst_gpio_keys.nbuttons = good;
+                return platform_device_register(&pb_device);
+        }
+        return 0;
+}
+late_initcall(pb_keys_init);
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
new file mode 100644
index 000000000000..32cd7edd71a0
--- /dev/null
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -0,0 +1,165 @@
+/*
+ * vrtc.c: Driver for virtual RTC device on Intel MID platform
+ *
+ * (C) Copyright 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ * VRTC is emulated by system controller firmware, the real HW
+ * RTC is located in the PMIC device. SCU FW shadows PMIC RTC
+ * in a memory mapped IO space that is visible to the host IA
+ * processor.
+ *
+ * This driver is based on RTC CMOS driver.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+
+#include <asm/mrst.h>
+#include <asm/mrst-vrtc.h>
+#include <asm/time.h>
+#include <asm/fixmap.h>
+
+static unsigned char __iomem *vrtc_virt_base;
+
+unsigned char vrtc_cmos_read(unsigned char reg)
+{
+        unsigned char retval;
+
+        /* vRTC's registers range from 0x0 to 0xD */
+        if (reg > 0xd || !vrtc_virt_base)
+                return 0xff;
+
+        lock_cmos_prefix(reg);
+        retval = __raw_readb(vrtc_virt_base + (reg << 2));
+        lock_cmos_suffix(reg);
+        return retval;
+}
+EXPORT_SYMBOL_GPL(vrtc_cmos_read);
+
+void vrtc_cmos_write(unsigned char val, unsigned char reg)
+{
+        if (reg > 0xd || !vrtc_virt_base)
+                return;
+
+        lock_cmos_prefix(reg);
+        __raw_writeb(val, vrtc_virt_base + (reg << 2));
+        lock_cmos_suffix(reg);
+}
+EXPORT_SYMBOL_GPL(vrtc_cmos_write);
+
+unsigned long vrtc_get_time(void)
+{
+        u8 sec, min, hour, mday, mon;
+        u32 year;
+
+        while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP))
+                cpu_relax();
+
+        sec = vrtc_cmos_read(RTC_SECONDS);
+        min = vrtc_cmos_read(RTC_MINUTES);
+        hour = vrtc_cmos_read(RTC_HOURS);
+        mday = vrtc_cmos_read(RTC_DAY_OF_MONTH);
+        mon = vrtc_cmos_read(RTC_MONTH);
+        year = vrtc_cmos_read(RTC_YEAR);
+
+        /* vRTC YEAR reg contains the offset to 1960 */
+        year += 1960;
+
+        printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
+                "mon: %d year: %d\n", sec, min, hour, mday, mon, year);
+
+        return mktime(year, mon, mday, hour, min, sec);
+}
+
+/* Only care about the minutes and seconds */
+int vrtc_set_mmss(unsigned long nowtime)
+{
+        int real_sec, real_min;
+        int vrtc_min;
+
+        vrtc_min = vrtc_cmos_read(RTC_MINUTES);
+
+        real_sec = nowtime % 60;
+        real_min = nowtime / 60;
+        if (((abs(real_min - vrtc_min) + 15)/30) & 1)
+                real_min += 30;
+        real_min %= 60;
+
+        vrtc_cmos_write(real_sec, RTC_SECONDS);
+        vrtc_cmos_write(real_min, RTC_MINUTES);
+        return 0;
+}
+
+void __init mrst_rtc_init(void)
+{
+        unsigned long rtc_paddr;
+        void __iomem *virt_base;
+
+        sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+        if (!sfi_mrtc_num)
+                return;
+
+        rtc_paddr = sfi_mrtc_array[0].phys_addr;
+
+        /* vRTC's register address may not be page aligned */
+        set_fixmap_nocache(FIX_LNW_VRTC, rtc_paddr);
+
+        virt_base = (void __iomem *)__fix_to_virt(FIX_LNW_VRTC);
+        virt_base += rtc_paddr & ~PAGE_MASK;
+        vrtc_virt_base = virt_base;
+
+        x86_platform.get_wallclock = vrtc_get_time;
+        x86_platform.set_wallclock = vrtc_set_mmss;
+}
+
+/*
+ * The Moorestown platform has a memory mapped virtual RTC device that emulates
+ * the programming interface of the RTC.
+ */
+
+static struct resource vrtc_resources[] = {
+        [0] = {
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .flags  = IORESOURCE_IRQ,
+        }
+};
+
+static struct platform_device vrtc_device = {
+        .name           = "rtc_mrst",
+        .id             = -1,
+        .resource       = vrtc_resources,
+        .num_resources  = ARRAY_SIZE(vrtc_resources),
+};
+
+/* Register the RTC device if appropriate */
+static int __init mrst_device_create(void)
+{
+        /* No Moorestown, no device */
+        if (!mrst_identify_cpu())
+                return -ENODEV;
+        /* No timer, no device */
+        if (!sfi_mrtc_num)
+                return -ENODEV;
+
+        /* iomem resource */
+        vrtc_resources[0].start = sfi_mrtc_array[0].phys_addr;
+        vrtc_resources[0].end = sfi_mrtc_array[0].phys_addr +
+                                MRST_VRTC_MAP_SZ;
+        /* irq resource */
+        vrtc_resources[1].start = sfi_mrtc_array[0].irq;
+        vrtc_resources[1].end = sfi_mrtc_array[0].irq;
+
+        return platform_device_register(&vrtc_device);
+}
+
+module_init(mrst_device_create);
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index dd4c281ffe57..7785b72ecc3a 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -34,23 +34,12 @@
 #ifdef CONFIG_X86_LOCAL_APIC
 static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 
-static void __init mp_sfi_register_lapic_address(unsigned long address)
-{
-        mp_lapic_addr = address;
-
-        set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
-        if (boot_cpu_physical_apicid == -1U)
-                boot_cpu_physical_apicid = read_apic_id();
-
-        pr_info("Boot CPU = %d\n", boot_cpu_physical_apicid);
-}
-
 /* All CPUs enumerated by SFI must be present and enabled */
 static void __cpuinit mp_sfi_register_lapic(u8 id)
 {
-        if (MAX_APICS - id <= 0) {
+        if (MAX_LOCAL_APIC - id <= 0) {
                 pr_warning("Processor #%d invalid (max %d)\n",
-                        id, MAX_APICS);
+                        id, MAX_LOCAL_APIC);
                 return;
         }
 
@@ -110,7 +99,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 int __init sfi_platform_init(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-        mp_sfi_register_lapic_address(sfi_lapic_addr);
+        register_lapic_address(sfi_lapic_addr);
         sfi_table_parse(SFI_SIG_CPUS, NULL, NULL, sfi_parse_cpus);
 #endif
 #ifdef CONFIG_X86_IO_APIC
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ba9caa808a9c..df58e9cad96a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1341,7 +1341,7 @@ uv_activation_descriptor_init(int node, int pnode)
 
         /*
          * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
-         * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub
+         * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE)
          */
         bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE
                                 * UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
@@ -1490,7 +1490,7 @@ calculate_destination_timeout(void)
 /*
  * initialize the bau_control structure for each cpu
  */
-static void __init uv_init_per_cpu(int nuvhubs)
+static int __init uv_init_per_cpu(int nuvhubs)
 {
         int i;
         int cpu;
@@ -1507,7 +1507,7 @@ static void __init uv_init_per_cpu(int nuvhubs)
         struct bau_control *smaster = NULL;
         struct socket_desc {
                 short num_cpus;
-                short cpu_number[16];
+                short cpu_number[MAX_CPUS_PER_SOCKET];
         };
         struct uvhub_desc {
                 unsigned short socket_mask;
@@ -1540,6 +1540,10 @@ static void __init uv_init_per_cpu(int nuvhubs)
                 sdp = &bdp->socket[socket];
                 sdp->cpu_number[sdp->num_cpus] = cpu;
                 sdp->num_cpus++;
+                if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) {
+                        printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus);
+                        return 1;
+                }
         }
         for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
                 if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8))))
@@ -1570,6 +1574,12 @@ static void __init uv_init_per_cpu(int nuvhubs)
                                 bcp->uvhub_master = hmaster;
                                 bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->
                                                 blade_processor_id;
+                                if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
+                                        printk(KERN_EMERG
+                                                "%d cpus per uvhub invalid\n",
+                                                bcp->uvhub_cpu);
+                                        return 1;
+                                }
                         }
 nextsocket:
                         socket++;
@@ -1595,6 +1605,7 @@ nextsocket:
                 bcp->congested_reps = congested_reps;
                 bcp->congested_period = congested_period;
         }
+        return 0;
 }
 
 /*
@@ -1625,7 +1636,10 @@ static int __init uv_bau_init(void)
         spin_lock_init(&disable_lock);
         congested_cycles = microsec_2_cycles(congested_response_us);
 
-        uv_init_per_cpu(nuvhubs);
+        if (uv_init_per_cpu(nuvhubs)) {
+                nobau = 1;
+                return 0;
+        }
 
         uv_partition_base_pnode = 0x7fffffff;
         for (uvhub = 0; uvhub < nuvhubs; uvhub++)
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index 3371bd053b89..632037671746 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -171,7 +171,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
         ver = m->apicver;
         if ((ver >= 0x14 && m->apicid >= 0xff) || m->apicid >= 0xf) {
                 printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n",
-                        m->apicid, MAX_APICS);
+                        m->apicid, MAX_LOCAL_APIC);
                 return;
         }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 44dcad43989d..7e8d3bc80af6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -574,8 +574,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
 
         preempt_disable();
 
-        start = __get_cpu_var(idt_desc).address;
-        end = start + __get_cpu_var(idt_desc).size + 1;
+        start = __this_cpu_read(idt_desc.address);
+        end = start + __this_cpu_read(idt_desc.size) + 1;
 
         xen_mc_flush();
 
@@ -1174,6 +1174,15 @@ asmlinkage void __init xen_start_kernel(void)
 
         xen_smp_init();
 
+#ifdef CONFIG_ACPI_NUMA
+        /*
+         * The pages we from Xen are not related to machine pages, so
+         * any NUMA information the kernel tries to get from ACPI will
+         * be meaningless.  Prevent it from trying.
+         */
+        acpi_numa = -1;
+#endif
+
         pgd = (pgd_t *)xen_start_info->pt_base;
 
         if (!xen_initial_domain())
@@ -1256,25 +1265,6 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-static 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;
-}
-
 static int init_hvm_pv_info(int *major, int *minor)
 {
         uint32_t eax, ebx, ecx, edx, pages, msr, base;
@@ -1384,6 +1374,18 @@ static bool __init xen_hvm_platform(void)
         return true;
 }
 
+bool xen_hvm_need_lapic(void)
+{
+        if (xen_pv_domain())
+                return false;
+        if (!xen_hvm_domain())
+                return false;
+        if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
+                return false;
+        return true;
+}
+EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
+
 const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = {
         .name                   = "Xen HVM",
         .detect                 = xen_hvm_platform,
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 9e565da5d1f7..4ec8035e3216 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -22,7 +22,7 @@ static inline void xen_mc_batch(void)
         unsigned long flags;
         /* need to disable interrupts until this entry is complete */
         local_irq_save(flags);
-        __get_cpu_var(xen_mc_irq_flags) = flags;
+        __this_cpu_write(xen_mc_irq_flags, flags);
 }
 
 static inline struct multicall_space xen_mc_entry(size_t args)
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 23e061b9327b..cc9b1e182fcf 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -159,8 +159,8 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
 {
         struct xen_spinlock *prev;
 
-        prev = __get_cpu_var(lock_spinners);
-        __get_cpu_var(lock_spinners) = xl;
+        prev = __this_cpu_read(lock_spinners);
+        __this_cpu_write(lock_spinners, xl);
 
         wmb();                  /* set lock of interest before count */
 
@@ -179,14 +179,14 @@ static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock
         asm(LOCK_PREFIX " decw %0"
             : "+m" (xl->spinners) : : "memory");
         wmb();                  /* decrement count before restoring lock */
-        __get_cpu_var(lock_spinners) = prev;
+        __this_cpu_write(lock_spinners, prev);
 }
 
 static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable)
 {
         struct xen_spinlock *xl = (struct xen_spinlock *)lock;
         struct xen_spinlock *prev;
-        int irq = __get_cpu_var(lock_kicker_irq);
+        int irq = __this_cpu_read(lock_kicker_irq);
         int ret;
         u64 start;
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5da5e53fb94c..067759e3d6a5 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -135,24 +135,24 @@ static void do_stolen_accounting(void)
 
         /* Add the appropriate number of ticks of stolen time,
            including any left-overs from last time. */
-        stolen = runnable + offline + __get_cpu_var(xen_residual_stolen);
+        stolen = runnable + offline + __this_cpu_read(xen_residual_stolen);
 
         if (stolen < 0)
                 stolen = 0;
 
         ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
-        __get_cpu_var(xen_residual_stolen) = stolen;
+        __this_cpu_write(xen_residual_stolen, stolen);
         account_steal_ticks(ticks);
 
         /* Add the appropriate number of ticks of blocked time,
            including any left-overs from last time. */
-        blocked += __get_cpu_var(xen_residual_blocked);
+        blocked += __this_cpu_read(xen_residual_blocked);
 
         if (blocked < 0)
                 blocked = 0;
 
         ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
-        __get_cpu_var(xen_residual_blocked) = blocked;
+        __this_cpu_write(xen_residual_blocked, blocked);
         account_idle_ticks(ticks);
 }