Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

153 files changed, 4496 insertions, 2334 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 92091de11113..610001d385dd 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -29,6 +29,7 @@
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mpspec.h>
+#include <asm/trampoline.h>
 
 #define COMPILER_DEPENDENT_INT64   long long
 #define COMPILER_DEPENDENT_UINT64  unsigned long long
@@ -88,11 +89,15 @@ extern int acpi_disabled;
 extern int acpi_pci_disabled;
 extern int acpi_skip_timer_override;
 extern int acpi_use_timer_override;
+extern int acpi_fix_pin2_polarity;
 
 extern u8 acpi_sci_flags;
 extern int acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
+extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
+                                  int trigger, int polarity);
+
 static inline void disable_acpi(void)
 {
         acpi_disabled = 1;
@@ -109,11 +114,11 @@ static inline void acpi_disable_pci(void)
         acpi_noirq_set();
 }
 
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern void acpi_restore_state_mem(void);
+/* Low-level suspend routine. */
+extern int acpi_suspend_lowlevel(void);
 
-extern unsigned long acpi_wakeup_address;
+extern const unsigned char acpi_wakeup_code[];
+#define acpi_wakeup_address (__pa(TRAMPOLINE_SYM(acpi_wakeup_code)))
 
 /* early initialization routine */
 extern void acpi_reserve_wakeup_memory(void);
@@ -134,7 +139,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
             boot_cpu_data.x86_model <= 0x05 &&
             boot_cpu_data.x86_mask < 0x0A)
                 return 1;
-        else if (c1e_detected)
+        else if (amd_e400_c1e_detected)
                 return 1;
         else
                 return max_cstate;
@@ -178,21 +183,10 @@ static inline void disable_acpi(void) { }
 
 #define ARCH_HAS_POWER_INIT     1
 
-struct bootnode;
-
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
-extern int acpi_get_nodes(struct bootnode *physnodes);
-extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-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
+extern int x86_acpi_numa_init(void);
+#endif /* CONFIG_ACPI_NUMA */
 
 #define acpi_unlazy_tlb(x)      leave_mm(x)
 
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index a63a68be1cce..94d420b360d1 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -15,4 +15,13 @@
         .endm
 #endif
 
+.macro altinstruction_entry orig alt feature orig_len alt_len
+        .align 8
+        .quad \orig
+        .quad \alt
+        .word \feature
+        .byte \orig_len
+        .byte \alt_len
+.endm
+
 #endif  /*  __ASSEMBLY__  */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index bc6abb7bc7ee..bf535f947e8c 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -65,6 +65,7 @@ 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,
@@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end  NULL
 #endif
 
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
  * Allows the kernel to edit read-only pages.
@@ -177,7 +180,14 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  * 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);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 5af2982133b5..a6863a2dec1f 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -24,11 +24,11 @@
 
 #ifdef CONFIG_AMD_IOMMU
 
-extern void amd_iommu_detect(void);
+extern int amd_iommu_detect(void);
 
 #else
 
-static inline void amd_iommu_detect(void) { }
+static inline int amd_iommu_detect(void) { return -ENODEV; }
 
 #endif
 
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index cb030374b90a..55d95eb789b3 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -19,13 +19,12 @@
 #ifndef _ASM_X86_AMD_IOMMU_PROTO_H
 #define _ASM_X86_AMD_IOMMU_PROTO_H
 
-struct amd_iommu;
+#include <asm/amd_iommu_types.h>
 
 extern int amd_iommu_init_dma_ops(void);
 extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_flush_all_domains(void);
-extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_apply_erratum_63(u16 devid);
 extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
@@ -44,4 +43,12 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev)
                (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
 }
 
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+        if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+                return false;
+
+        return !!(iommu->features & f);
+}
+
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 08616180deaf..4c9982995414 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -68,12 +68,25 @@
 #define MMIO_CONTROL_OFFSET     0x0018
 #define MMIO_EXCL_BASE_OFFSET   0x0020
 #define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_EXT_FEATURES       0x0030
 #define MMIO_CMD_HEAD_OFFSET    0x2000
 #define MMIO_CMD_TAIL_OFFSET    0x2008
 #define MMIO_EVT_HEAD_OFFSET    0x2010
 #define MMIO_EVT_TAIL_OFFSET    0x2018
 #define MMIO_STATUS_OFFSET      0x2020
 
+
+/* Extended Feature Bits */
+#define FEATURE_PREFETCH        (1ULL<<0)
+#define FEATURE_PPR             (1ULL<<1)
+#define FEATURE_X2APIC          (1ULL<<2)
+#define FEATURE_NX              (1ULL<<3)
+#define FEATURE_GT              (1ULL<<4)
+#define FEATURE_IA              (1ULL<<6)
+#define FEATURE_GA              (1ULL<<7)
+#define FEATURE_HE              (1ULL<<8)
+#define FEATURE_PC              (1ULL<<9)
+
 /* MMIO status bits */
 #define MMIO_STATUS_COM_WAIT_INT_MASK   0x04
 
@@ -113,7 +126,9 @@
 /* command specific defines */
 #define CMD_COMPL_WAIT          0x01
 #define CMD_INV_DEV_ENTRY       0x02
-#define CMD_INV_IOMMU_PAGES     0x03
+#define CMD_INV_IOMMU_PAGES     0x03
+#define CMD_INV_IOTLB_PAGES     0x04
+#define CMD_INV_ALL             0x08
 
 #define CMD_COMPL_WAIT_STORE_MASK       0x01
 #define CMD_COMPL_WAIT_INT_MASK         0x02
@@ -215,6 +230,8 @@
 #define IOMMU_PTE_IR (1ULL << 61)
 #define IOMMU_PTE_IW (1ULL << 62)
 
+#define DTE_FLAG_IOTLB  0x01
+
 #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
 #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
 #define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
@@ -227,6 +244,7 @@
 /* IOMMU capabilities */
 #define IOMMU_CAP_IOTLB   24
 #define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR     27
 
 #define MAX_DOMAIN_ID 65536
 
@@ -249,6 +267,8 @@ extern bool amd_iommu_dump;
 
 /* global flag if IOMMUs cache non-present entries */
 extern bool amd_iommu_np_cache;
+/* Only true if all IOMMUs support device IOTLBs */
+extern bool amd_iommu_iotlb_sup;
 
 /*
  * Make iterating over all IOMMUs easier
@@ -371,6 +391,9 @@ struct amd_iommu {
         /* flags read from acpi table */
         u8 acpi_flags;
 
+        /* Extended features */
+        u64 features;
+
         /*
          * Capability pointer. There could be more than one IOMMU per PCI
          * device function if there are more than one AMD IOMMU capability
@@ -409,20 +432,26 @@ struct amd_iommu {
         /* if one, we need to send a completion wait command */
         bool need_sync;
 
-        /* becomes true if a command buffer reset is running */
-        bool reset_in_progress;
-
         /* default dma_ops domain for that IOMMU */
         struct dma_ops_domain *default_dom;
 
         /*
-         * This array is required to work around a potential BIOS bug.
-         * The BIOS may miss to restore parts of the PCI configuration
-         * space when the system resumes from S3. The result is that the
-         * IOMMU does not execute commands anymore which leads to system
-         * failure.
+         * We can't rely on the BIOS to restore all values on reinit, so we
+         * need to stash them
          */
-        u32 cache_cfg[4];
+
+        /* The iommu BAR */
+        u32 stored_addr_lo;
+        u32 stored_addr_hi;
+
+        /*
+         * Each iommu has 6 l1s, each of which is documented as having 0x12
+         * registers
+         */
+        u32 stored_l1[6][0x12];
+
+        /* The l2 indirect registers */
+        u32 stored_l2[0x83];
 };
 
 /*
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
new file mode 100644
index 000000000000..67f87f257611
--- /dev/null
+++ b/arch/x86/include/asm/amd_nb.h
@@ -0,0 +1,64 @@
+#ifndef _ASM_X86_AMD_NB_H
+#define _ASM_X86_AMD_NB_H
+
+#include <linux/pci.h>
+
+struct amd_nb_bus_dev_range {
+        u8 bus;
+        u8 dev_base;
+        u8 dev_limit;
+};
+
+extern const struct pci_device_id amd_nb_misc_ids[];
+extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
+
+extern bool early_is_amd_nb(u32 value);
+extern int amd_cache_northbridges(void);
+extern void amd_flush_garts(void);
+extern int amd_numa_init(void);
+extern int amd_get_subcaches(int);
+extern int amd_set_subcaches(int, int);
+
+struct amd_northbridge {
+        struct pci_dev *misc;
+        struct pci_dev *link;
+};
+
+struct amd_northbridge_info {
+        u16 num;
+        u64 flags;
+        struct amd_northbridge *nb;
+};
+extern struct amd_northbridge_info amd_northbridges;
+
+#define AMD_NB_GART                     BIT(0)
+#define AMD_NB_L3_INDEX_DISABLE         BIT(1)
+#define AMD_NB_L3_PARTITIONING          BIT(2)
+
+#ifdef CONFIG_AMD_NB
+
+static inline u16 amd_nb_num(void)
+{
+        return amd_northbridges.num;
+}
+
+static inline bool amd_nb_has_feature(unsigned feature)
+{
+        return ((amd_northbridges.flags & feature) == feature);
+}
+
+static inline struct amd_northbridge *node_to_amd_nb(int node)
+{
+        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
+
+
+#endif /* _ASM_X86_AMD_NB_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index a69b1ac9eaf8..af60d8a2e288 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -54,7 +54,6 @@ extern struct clock_event_device *global_clock_event;
 extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
-extern unsigned int boot_cpu_id;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
@@ -63,7 +62,7 @@ extern int sfi_mtimer_num;
 #else /* CONFIG_APB_TIMER */
 
 static inline unsigned long apbt_quick_calibrate(void) {return 0; }
-static inline void apbt_time_init(void) {return 0; }
+static inline void apbt_time_init(void) { }
 
 #endif
 #endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1fa03e04ae44..4a0b7c7e2cce 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
-#include <linux/delay.h>
 #include <linux/pm.h>
 
 #include <asm/alternative.h>
@@ -141,13 +140,13 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 
 static inline u32 native_apic_msr_read(u32 reg)
 {
-        u32 low, high;
+        u64 msr;
 
         if (reg == APIC_DFR)
                 return -1;
 
-        rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
-        return low;
+        rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+        return (u32)msr;
 }
 
 static inline void native_x2apic_wait_icr_idle(void)
@@ -181,12 +180,12 @@ extern void enable_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
-        int msr, msr2;
+        u64 msr;
 
         if (!cpu_has_x2apic)
                 return 0;
 
-        rdmsr(MSR_IA32_APICBASE, msr, msr2);
+        rdmsrl(MSR_IA32_APICBASE, msr);
         if (msr & X2APIC_ENABLE)
                 return 1;
         return 0;
@@ -220,7 +219,6 @@ extern void enable_IR_x2apic(void);
 
 extern int get_physical_broadcast(void);
 
-extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -228,22 +226,22 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
 extern void disable_local_APIC(void);
 extern void lapic_shutdown(void);
 extern int verify_local_APIC(void);
-extern void cache_APIC_registers(void);
 extern void sync_Arb_IDs(void);
 extern void init_bsp_APIC(void);
 extern void setup_local_APIC(void);
 extern void end_local_APIC_setup(void);
+extern void bsp_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(unsigned long addr);
 
 /*
  * 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)
@@ -252,16 +250,13 @@ static inline int apic_is_clustered_box(void)
 }
 #endif
 
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok          1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-static inline void apic_disable(void) { }
 # define setup_boot_APIC_clock x86_init_noop
 # define setup_secondary_APIC_clock x86_init_noop
 #endif /* !CONFIG_X86_LOCAL_APIC */
@@ -307,8 +302,6 @@ struct apic {
 
         void (*setup_apic_routing)(void);
         int (*multi_timer_check)(int apic, int irq);
-        int (*apicid_to_node)(int logical_apicid);
-        int (*cpu_to_logical_apicid)(int cpu);
         int (*cpu_present_to_apicid)(int mps_cpu);
         void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
         void (*setup_portio_remap)(void);
@@ -356,6 +349,28 @@ struct apic {
         void (*icr_write)(u32 low, u32 high);
         void (*wait_icr_idle)(void);
         u32 (*safe_wait_icr_idle)(void);
+
+#ifdef CONFIG_X86_32
+        /*
+         * Called very early during boot from get_smp_config().  It should
+         * return the logical apicid.  x86_[bios]_cpu_to_apicid is
+         * initialized before this function is called.
+         *
+         * If logical apicid can't be determined that early, the function
+         * may return BAD_APICID.  Logical apicid will be configured after
+         * init_apic_ldr() while bringing up CPUs.  Note that NUMA affinity
+         * won't be applied properly during early boot in this case.
+         */
+        int (*x86_32_early_logical_apicid)(int cpu);
+
+        /*
+         * Optional method called from setup_local_APIC() after logical
+         * apicid is guaranteed to be known to initialize apicid -> node
+         * mapping if NUMA initialization hasn't done so already.  Don't
+         * add new users.
+         */
+        int (*x86_32_numa_cpu_node)(int cpu);
+#endif
 };
 
 /*
@@ -366,6 +381,26 @@ struct apic {
 extern struct apic *apic;
 
 /*
+ * APIC drivers are probed based on how they are listed in the .apicdrivers
+ * section. So the order is important and enforced by the ordering
+ * of different apic driver files in the Makefile.
+ *
+ * For the files having two apic drivers, we use apic_drivers()
+ * to enforce the order with in them.
+ */
+#define apic_driver(sym)                                        \
+        static struct apic *__apicdrivers_##sym __used          \
+        __aligned(sizeof(struct apic *))                        \
+        __section(.apicdrivers) = { &sym }
+
+#define apic_drivers(sym1, sym2)                                        \
+        static struct apic *__apicdrivers_##sym1##sym2[2] __used        \
+        __aligned(sizeof(struct apic *))                                \
+        __section(.apicdrivers) = { &sym1, &sym2 }
+
+extern struct apic *__apicdrivers[], *__apicdrivers_end[];
+
+/*
  * APIC functionality to boot other CPUs - only used on SMP:
  */
 #ifdef CONFIG_SMP
@@ -443,15 +478,10 @@ static inline unsigned default_get_apic_id(unsigned long x)
 #define DEFAULT_TRAMPOLINE_PHYS_HIGH            0x469
 
 #ifdef CONFIG_X86_64
-extern struct apic apic_flat;
-extern struct apic apic_physflat;
-extern struct apic apic_x2apic_cluster;
-extern struct apic apic_x2apic_phys;
 extern int default_acpi_madt_oem_check(char *, char *);
 
 extern void apic_send_IPI_self(int vector);
 
-extern struct apic apic_x2apic_uv_x;
 DECLARE_PER_CPU(int, x2apic_extra_bits);
 
 extern int default_cpu_present_to_apicid(int mps_cpu);
@@ -465,7 +495,7 @@ static inline void default_wait_for_init_deassert(atomic_t *deassert)
         return;
 }
 
-extern void generic_bigsmp_probe(void);
+extern struct apic *generic_bigsmp_probe(void);
 
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -501,7 +531,10 @@ extern struct apic apic_noop;
 
 #ifdef CONFIG_X86_32
 
-extern struct apic apic_default;
+static inline int noop_x86_32_early_logical_apicid(int cpu)
+{
+        return BAD_APICID;
+}
 
 /*
  * Set up the logical destination ID.
@@ -522,8 +555,6 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
         return cpuid_apic >> index_msb;
 }
 
-extern int default_apicid_to_node(int logical_apicid);
-
 #endif
 
 static inline unsigned int
@@ -558,12 +589,6 @@ static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_ma
         *retmap = *phys_map;
 }
 
-/* Mapping from cpu number to logical apicid */
-static inline int default_cpu_to_logical_apicid(int cpu)
-{
-        return 1 << cpu;
-}
-
 static inline int __default_cpu_present_to_apicid(int mps_cpu)
 {
         if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
@@ -596,8 +621,4 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_32
-extern u8 cpu_2_logical_apicid[NR_CPUS];
-#endif
-
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7fe3b3060f08..34595d5e1038 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -78,6 +78,7 @@
 #define         APIC_DEST_LOGICAL       0x00800
 #define         APIC_DEST_PHYSICAL      0x00000
 #define         APIC_DM_FIXED           0x00000
+#define         APIC_DM_FIXED_MASK      0x00700
 #define         APIC_DM_LOWEST          0x00100
 #define         APIC_DM_SMI             0x00200
 #define         APIC_DM_REMRD           0x00300
@@ -131,6 +132,7 @@
 #define APIC_EILVTn(n)  (0x500 + 0x10 * n)
 #define         APIC_EILVT_NR_AMD_K8    1       /* # of extended interrupts */
 #define         APIC_EILVT_NR_AMD_10H   4
+#define         APIC_EILVT_NR_MAX       APIC_EILVT_NR_AMD_10H
 #define         APIC_EILVT_LVTOFF(x)    (((x) >> 4) & 0xF)
 #define         APIC_EILVT_MSG_FIX      0x0
 #define         APIC_EILVT_MSG_SMI      0x2
@@ -144,6 +146,7 @@
 
 #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
@@ -424,4 +427,16 @@ struct local_apic {
 #else
  #define BAD_APICID 0xFFFFu
 #endif
+
+enum ioapic_irq_destination_types {
+        dest_Fixed              = 0,
+        dest_LowestPrio         = 1,
+        dest_SMI                = 2,
+        dest__reserved_1        = 3,
+        dest_NMI                = 4,
+        dest_INIT               = 5,
+        dest__reserved_2        = 6,
+        dest_ExtINT             = 7
+};
+
 #endif /* _ASM_X86_APICDEF_H */
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index 3c7521063d3f..aa6a3170ab5a 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -4,16 +4,40 @@
 #include <asm/io.h>
 
 /*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E.
+ * Returns physical address of EBDA.  Returns 0 if there is no EBDA.
  */
 static inline unsigned int get_bios_ebda(void)
 {
+        /*
+         * There is a real-mode segmented pointer pointing to the
+         * 4K EBDA area at 0x40E.
+         */
         unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
         address <<= 4;
         return address; /* 0 means none */
 }
 
+/*
+ * Return the sanitized length of the EBDA in bytes, if it exists.
+ */
+static inline unsigned int get_bios_ebda_length(void)
+{
+        unsigned int address;
+        unsigned int length;
+
+        address = get_bios_ebda();
+        if (!address)
+                return 0;
+
+        /* EBDA length is byte 0 of the EBDA (stored in KiB) */
+        length = *(unsigned char *)phys_to_virt(address);
+        length <<= 10;
+
+        /* Trim the length if it extends beyond 640KiB */
+        length = min_t(unsigned int, (640 * 1024) - address, length);
+        return length;
+}
+
 void reserve_ebda_region(void);
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index bafd80defa43..69d58131bc8e 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -440,6 +440,8 @@ static inline int fls(int x)
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/find.h>
+
 #include <asm-generic/bitops/sched.h>
 
 #define ARCH_HAS_FAST_MULTIPLIER 1
@@ -454,14 +456,12 @@ static inline int fls(int x)
 
 #ifdef __KERNEL__
 
-#include <asm-generic/bitops/ext2-non-atomic.h>
+#include <asm-generic/bitops/le.h>
 
 #define ext2_set_bit_atomic(lock, nr, addr)                     \
         test_and_set_bit((nr), (unsigned long *)(addr))
 #define ext2_clear_bit_atomic(lock, nr, addr)                   \
         test_and_clear_bit((nr), (unsigned long *)(addr))
 
-#include <asm-generic/bitops/minix.h>
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_BITOPS_H */
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3b62ab56c7a0..5e1a2eef3e7c 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -32,11 +32,7 @@
 #define BOOT_HEAP_SIZE             0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
 
-#ifdef CONFIG_X86_64
-#define BOOT_HEAP_SIZE  0x7000
-#else
-#define BOOT_HEAP_SIZE  0x4000
-#endif
+#define BOOT_HEAP_SIZE  0x8000
 
 #endif /* !CONFIG_KERNEL_BZIP2 */
 
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 8e6218550e77..e020d88ec02d 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -12,6 +12,7 @@
 /* setup data types */
 #define SETUP_NONE                      0
 #define SETUP_E820_EXT                  1
+#define SETUP_DTB                       2
 
 /* extensible setup data list node */
 struct setup_data {
@@ -124,6 +125,7 @@ enum {
         X86_SUBARCH_LGUEST,
         X86_SUBARCH_XEN,
         X86_SUBARCH_MRST,
+        X86_SUBARCH_CE4100,
         X86_NR_SUBARCHS,
 };
 
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 63e35ec9075c..4e12668711e5 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -1,48 +1,8 @@
 #ifndef _ASM_X86_CACHEFLUSH_H
 #define _ASM_X86_CACHEFLUSH_H
 
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
 /* Caches aren't brain-dead on the intel. */
-static inline void flush_cache_all(void) { }
-static inline void flush_cache_mm(struct mm_struct *mm) { }
-static inline void flush_cache_dup_mm(struct mm_struct *mm) { }
-static inline void flush_cache_range(struct vm_area_struct *vma,
-                                     unsigned long start, unsigned long end) { }
-static inline void flush_cache_page(struct vm_area_struct *vma,
-                                    unsigned long vmaddr, unsigned long pfn) { }
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-static inline void flush_dcache_page(struct page *page) { }
-static inline void flush_dcache_mmap_lock(struct address_space *mapping) { }
-static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { }
-static inline void flush_icache_range(unsigned long start,
-                                      unsigned long end) { }
-static inline void flush_icache_page(struct vm_area_struct *vma,
-                                     struct page *page) { }
-static inline void flush_icache_user_range(struct vm_area_struct *vma,
-                                           struct page *page,
-                                           unsigned long addr,
-                                           unsigned long len) { }
-static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
-static inline void flush_cache_vunmap(unsigned long start,
-                                      unsigned long end) { }
-
-static inline void copy_to_user_page(struct vm_area_struct *vma,
-                                     struct page *page, unsigned long vaddr,
-                                     void *dst, const void *src,
-                                     unsigned long len)
-{
-        memcpy(dst, src, len);
-}
-
-static inline void copy_from_user_page(struct vm_area_struct *vma,
-                                       struct page *page, unsigned long vaddr,
-                                       void *dst, const void *src,
-                                       unsigned long len)
-{
-        memcpy(dst, src, len);
-}
+#include <asm-generic/cacheflush.h>
 
 #ifdef CONFIG_X86_PAT
 /*
@@ -111,7 +71,7 @@ static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
  * Read/Write    : ReadOnly, ReadWrite
  * Presence      : NotPresent
  *
- * Within a catagory, the attributes are mutually exclusive.
+ * Within a category, the attributes are mutually exclusive.
  *
  * The implementation of this API will take care of various aspects that
  * are associated with changing such attributes, such as:
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index 0918654305af..0d467b338835 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -62,9 +62,9 @@ struct cal_chipset_ops {
 extern int use_calgary;
 
 #ifdef CONFIG_CALGARY_IOMMU
-extern void detect_calgary(void);
+extern int detect_calgary(void);
 #else
-static inline void detect_calgary(void) { return; }
+static inline int detect_calgary(void) { return -ENODEV; }
 #endif
 
 #endif /* _ASM_X86_CALGARY_H */
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0e63c9a2a8d0..30af5a832163 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,36 +48,38 @@ For 32-bit we have the following conventions - kernel is built with
 
 
 /*
- * 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
+ * 64-bit system call stack frame layout defines and helpers, for
+ * assembly code (note that the seemingly unnecessary parentheses
+ * are to prevent cpp from inserting spaces in expressions that get
+ * passed to macros):
  */
 
-#define R15               0
-#define R14               8
-#define R13              16
-#define R12              24
-#define RBP              32
-#define RBX              40
+#define R15               (0)
+#define R14               (8)
+#define R13              (16)
+#define R12              (24)
+#define RBP              (32)
+#define RBX              (40)
 
 /* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11              48
-#define R10              56
-#define R9               64
-#define R8               72
-#define RAX              80
-#define RCX              88
-#define RDX              96
-#define RSI             104
-#define RDI             112
-#define ORIG_RAX        120       /* + error_code */
+#define R11              (48)
+#define R10              (56)
+#define R9               (64)
+#define R8               (72)
+#define RAX              (80)
+#define RCX              (88)
+#define RDX              (96)
+#define RSI             (104)
+#define RDI             (112)
+#define ORIG_RAX        (120)       /* + error_code */
 /* end of arguments */
 
 /* cpu exception frame or undefined in case of fast syscall: */
-#define RIP             128
-#define CS              136
-#define EFLAGS          144
-#define RSP             152
-#define SS              160
+#define RIP             (128)
+#define CS              (136)
+#define EFLAGS          (144)
+#define RSP             (152)
+#define SS              (160)
 
 #define ARGOFFSET       R11
 #define SWFRAME         ORIG_RAX
@@ -111,7 +113,7 @@ For 32-bit we have the following conventions - kernel is built with
         .endif
         .endm
 
-#define ARG_SKIP        9*8
+#define ARG_SKIP        (9*8)
 
         .macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
                             skipr8910=0, skiprdx=0
@@ -169,7 +171,7 @@ For 32-bit we have the following conventions - kernel is built with
         .endif
         .endm
 
-#define REST_SKIP       6*8
+#define REST_SKIP       (6*8)
 
         .macro SAVE_REST
         subq $REST_SKIP, %rsp
diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h
new file mode 100644
index 000000000000..e656ad8c0a2e
--- /dev/null
+++ b/arch/x86/include/asm/ce4100.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_CE4100_H_
+#define _ASM_CE4100_H_
+
+int ce4100_pci_init(void);
+
+#endif
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091bf19c..4564c8e28a33 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,6 @@ extern void arch_unregister_cpu(int);
 
 DECLARE_PER_CPU(int, cpu_state);
 
-extern unsigned int boot_cpu_id;
+int mwait_usable(const struct cpuinfo_x86 *);
 
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3f76523589af..71cc3800712c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -125,7 +125,7 @@
 #define X86_FEATURE_OSXSAVE     (4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX         (4*32+28) /* Advanced Vector Extensions */
 #define X86_FEATURE_F16C        (4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRND       (4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_RDRAND      (4*32+30) /* The RDRAND instruction */
 #define X86_FEATURE_HYPERVISOR  (4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
@@ -152,10 +152,15 @@
 #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
 #define X86_FEATURE_OSVW        (6*32+ 9) /* OS Visible Workaround */
 #define X86_FEATURE_IBS         (6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5        (6*32+11) /* SSE-5 */
+#define X86_FEATURE_XOP         (6*32+11) /* extended AVX instructions */
 #define X86_FEATURE_SKINIT      (6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT         (6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP         (6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4        (6*32+16) /* 4 operands MAC instructions */
 #define X86_FEATURE_NODEID_MSR  (6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM         (6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT     (6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -180,9 +185,18 @@
 #define X86_FEATURE_LBRV        (8*32+ 6) /* AMD LBR Virtualization support */
 #define X86_FEATURE_SVML        (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
 #define X86_FEATURE_NRIPS       (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE    (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_SMEP        (9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_ERMS        (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -195,8 +209,7 @@ extern const char * const x86_power_flags[32];
 #define test_cpu_cap(c, bit)                                            \
          test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define cpu_has(c, bit)                                                 \
-        (__builtin_constant_p(bit) &&                                   \
+#define REQUIRED_MASK_BIT_SET(bit)                                      \
          ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||     \
            (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||     \
            (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||     \
@@ -206,10 +219,16 @@ extern const char * const x86_power_flags[32];
            (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||     \
            (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||     \
            (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||     \
-           (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )      \
-          ? 1 :                                                         \
+           (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit)                                                 \
+        (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :  \
          test_cpu_cap(c, bit))
 
+#define this_cpu_has(bit)                                               \
+        (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :  \
+         x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
 #define boot_cpu_has(bit)       cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)     set_bit(bit, (unsigned long *)((c)->x86_capability))
@@ -268,6 +287,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xsave           boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_hypervisor      boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq       boot_cpu_has(X86_FEATURE_PCLMULQDQ)
+#define cpu_has_perfctr_core    boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg         1
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/desc.h b/arch/x86/include/asm/desc.h
index 617bd56b3070..7b439d9aea2a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -4,30 +4,33 @@
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
+
 #include <linux/smp.h>
 
-static inline void fill_ldt(struct desc_struct *desc,
-                            const struct user_desc *info)
-{
-        desc->limit0 = info->limit & 0x0ffff;
-        desc->base0 = info->base_addr & 0x0000ffff;
-
-        desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
-        desc->type = (info->read_exec_only ^ 1) << 1;
-        desc->type |= info->contents << 2;
-        desc->s = 1;
-        desc->dpl = 0x3;
-        desc->p = info->seg_not_present ^ 1;
-        desc->limit = (info->limit & 0xf0000) >> 16;
-        desc->avl = info->useable;
-        desc->d = info->seg_32bit;
-        desc->g = info->limit_in_pages;
-        desc->base2 = (info->base_addr & 0xff000000) >> 24;
+static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
+{
+        desc->limit0            = info->limit & 0x0ffff;
+
+        desc->base0             = (info->base_addr & 0x0000ffff);
+        desc->base1             = (info->base_addr & 0x00ff0000) >> 16;
+
+        desc->type              = (info->read_exec_only ^ 1) << 1;
+        desc->type             |= info->contents << 2;
+
+        desc->s                 = 1;
+        desc->dpl               = 0x3;
+        desc->p                 = info->seg_not_present ^ 1;
+        desc->limit             = (info->limit & 0xf0000) >> 16;
+        desc->avl               = info->useable;
+        desc->d                 = info->seg_32bit;
+        desc->g                 = info->limit_in_pages;
+
+        desc->base2             = (info->base_addr & 0xff000000) >> 24;
         /*
          * Don't allow setting of the lm bit. It is useless anyway
          * because 64bit system calls require __USER_CS:
          */
-        desc->l = 0;
+        desc->l                 = 0;
 }
 
 extern struct desc_ptr idt_descr;
@@ -36,6 +39,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
         struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
+
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
@@ -48,16 +52,16 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
                              unsigned dpl, unsigned ist, unsigned seg)
 {
-        gate->offset_low = PTR_LOW(func);
-        gate->segment = __KERNEL_CS;
-        gate->ist = ist;
-        gate->p = 1;
-        gate->dpl = dpl;
-        gate->zero0 = 0;
-        gate->zero1 = 0;
-        gate->type = type;
-        gate->offset_middle = PTR_MIDDLE(func);
-        gate->offset_high = PTR_HIGH(func);
+        gate->offset_low        = PTR_LOW(func);
+        gate->segment           = __KERNEL_CS;
+        gate->ist               = ist;
+        gate->p                 = 1;
+        gate->dpl               = dpl;
+        gate->zero0             = 0;
+        gate->zero1             = 0;
+        gate->type              = type;
+        gate->offset_middle     = PTR_MIDDLE(func);
+        gate->offset_high       = PTR_HIGH(func);
 }
 
 #else
@@ -66,8 +70,7 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
                              unsigned short seg)
 {
         gate->a = (seg << 16) | (base & 0xffff);
-        gate->b = (base & 0xffff0000) |
-                  (((0x80 | type | (dpl << 5)) & 0xff) << 8);
+        gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8);
 }
 
 #endif
@@ -75,31 +78,29 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
 static inline int desc_empty(const void *ptr)
 {
         const u32 *desc = ptr;
+
         return !(desc[0] | desc[1]);
 }
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define load_TR_desc() native_load_tr_desc()
-#define load_gdt(dtr) native_load_gdt(dtr)
-#define load_idt(dtr) native_load_idt(dtr)
-#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
-#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
-
-#define store_gdt(dtr) native_store_gdt(dtr)
-#define store_idt(dtr) native_store_idt(dtr)
-#define store_tr(tr) (tr = native_store_tr())
-
-#define load_TLS(t, cpu) native_load_tls(t, cpu)
-#define set_ldt native_set_ldt
-
-#define write_ldt_entry(dt, entry, desc)        \
-        native_write_ldt_entry(dt, entry, desc)
-#define write_gdt_entry(dt, entry, desc, type)          \
-        native_write_gdt_entry(dt, entry, desc, type)
-#define write_idt_entry(dt, entry, g)           \
-        native_write_idt_entry(dt, entry, g)
+#define load_TR_desc()                          native_load_tr_desc()
+#define load_gdt(dtr)                           native_load_gdt(dtr)
+#define load_idt(dtr)                           native_load_idt(dtr)
+#define load_tr(tr)                             asm volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt)                           asm volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr)                          native_store_gdt(dtr)
+#define store_idt(dtr)                          native_store_idt(dtr)
+#define store_tr(tr)                            (tr = native_store_tr())
+
+#define load_TLS(t, cpu)                        native_load_tls(t, cpu)
+#define set_ldt                                 native_set_ldt
+
+#define write_ldt_entry(dt, entry, desc)        native_write_ldt_entry(dt, entry, desc)
+#define write_gdt_entry(dt, entry, desc, type)  native_write_gdt_entry(dt, entry, desc, type)
+#define write_idt_entry(dt, entry, g)           native_write_idt_entry(dt, entry, g)
 
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
@@ -112,33 +113,27 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
 
 #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
 
-static inline void native_write_idt_entry(gate_desc *idt, int entry,
-                                          const gate_desc *gate)
+static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate)
 {
         memcpy(&idt[entry], gate, sizeof(*gate));
 }
 
-static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
-                                          const void *desc)
+static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc)
 {
         memcpy(&ldt[entry], desc, 8);
 }
 
-static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
-                                          const void *desc, int type)
+static inline void
+native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type)
 {
         unsigned int size;
+
         switch (type) {
-        case DESC_TSS:
-                size = sizeof(tss_desc);
-                break;
-        case DESC_LDT:
-                size = sizeof(ldt_desc);
-                break;
-        default:
-                size = sizeof(struct desc_struct);
-                break;
+        case DESC_TSS:  size = sizeof(tss_desc);        break;
+        case DESC_LDT:  size = sizeof(ldt_desc);        break;
+        default:        size = sizeof(*gdt);            break;
         }
+
         memcpy(&gdt[entry], desc, size);
 }
 
@@ -154,20 +149,21 @@ static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
 }
 
 
-static inline void set_tssldt_descriptor(void *d, unsigned long addr,
-                                         unsigned type, unsigned size)
+static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size)
 {
 #ifdef CONFIG_X86_64
         struct ldttss_desc64 *desc = d;
+
         memset(desc, 0, sizeof(*desc));
-        desc->limit0 = size & 0xFFFF;
-        desc->base0 = PTR_LOW(addr);
-        desc->base1 = PTR_MIDDLE(addr) & 0xFF;
-        desc->type = type;
-        desc->p = 1;
-        desc->limit1 = (size >> 16) & 0xF;
-        desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
-        desc->base3 = PTR_HIGH(addr);
+
+        desc->limit0            = size & 0xFFFF;
+        desc->base0             = PTR_LOW(addr);
+        desc->base1             = PTR_MIDDLE(addr) & 0xFF;
+        desc->type              = type;
+        desc->p                 = 1;
+        desc->limit1            = (size >> 16) & 0xF;
+        desc->base2             = (PTR_MIDDLE(addr) >> 8) & 0xFF;
+        desc->base3             = PTR_HIGH(addr);
 #else
         pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
 #endif
@@ -237,14 +233,16 @@ static inline void native_store_idt(struct desc_ptr *dtr)
 static inline unsigned long native_store_tr(void)
 {
         unsigned long tr;
+
         asm volatile("str %0":"=r" (tr));
+
         return tr;
 }
 
 static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 {
-        unsigned int i;
         struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+        unsigned int i;
 
         for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
                 gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
@@ -313,6 +311,7 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
                              unsigned dpl, unsigned ist, unsigned seg)
 {
         gate_desc s;
+
         pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
         /*
          * does not need to be atomic because it is only done once at
@@ -343,8 +342,9 @@ static inline void alloc_system_vector(int vector)
                 set_bit(vector, used_vectors);
                 if (first_system_vector > vector)
                         first_system_vector = vector;
-        } else
+        } else {
                 BUG();
+        }
 }
 
 static inline void alloc_intr_gate(unsigned int n, void *addr)
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index ca1098a7e580..0bdb0c54d9a1 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -10,7 +10,6 @@
 
 #include <linux/spinlock.h>     /* And spinlocks */
 #include <asm/io.h>             /* need byte IO */
-#include <linux/delay.h>
 
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
 #define dma_outb        outb_p
@@ -70,22 +69,18 @@
 
 #define MAX_DMA_CHANNELS        8
 
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
-
-#else
-
 /* 16MB ISA DMA zone */
 #define MAX_DMA_PFN   ((16 * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
 #define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
 
+#ifdef CONFIG_X86_32
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
+#else
 /* Compat define for old dma zone */
 #define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
 #endif
 
 /* 8237 DMA controllers */
@@ -151,6 +146,7 @@
 #define DMA_AUTOINIT            0x10
 
 
+#ifdef CONFIG_ISA_DMA_API
 extern spinlock_t  dma_spin_lock;
 
 static inline unsigned long claim_dma_lock(void)
@@ -164,6 +160,7 @@ static inline void release_dma_lock(unsigned long flags)
 {
         spin_unlock_irqrestore(&dma_spin_lock, flags);
 }
+#endif /* CONFIG_ISA_DMA_API */
 
 /* enable/disable a specific DMA channel */
 static inline void enable_dma(unsigned int dmanr)
@@ -303,9 +300,11 @@ static inline int get_dma_residue(unsigned int dmanr)
 }
 
 
-/* These are in kernel/dma.c: */
+/* These are in kernel/dma.c because x86 uses CONFIG_GENERIC_ISA_DMA */
+#ifdef CONFIG_ISA_DMA_API
 extern int request_dma(unsigned int dmanr, const char *device_id);
 extern void free_dma(unsigned int dmanr);
+#endif
 
 /* From PCI */
 
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 733f7e91e7a9..326099199318 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -89,6 +89,16 @@
         CFI_ADJUST_CFA_OFFSET -8
         .endm
 
+        .macro pushfq_cfi
+        pushfq
+        CFI_ADJUST_CFA_OFFSET 8
+        .endm
+
+        .macro popfq_cfi
+        popfq
+        CFI_ADJUST_CFA_OFFSET -8
+        .endm
+
         .macro movq_cfi reg offset=0
         movq %\reg, \offset(%rsp)
         CFI_REL_OFFSET \reg, \offset
@@ -109,6 +119,16 @@
         CFI_ADJUST_CFA_OFFSET -4
         .endm
 
+        .macro pushfl_cfi
+        pushfl
+        CFI_ADJUST_CFA_OFFSET 4
+        .endm
+
+        .macro popfl_cfi
+        popfl
+        CFI_ADJUST_CFA_OFFSET -4
+        .endm
+
         .macro movl_cfi reg offset=0
         movl %\reg, \offset(%esp)
         CFI_REL_OFFSET \reg, \offset
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec8a52d14ab1..908b96957d88 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -72,6 +72,9 @@ struct e820map {
 #define BIOS_BEGIN              0x000a0000
 #define BIOS_END                0x00100000
 
+#define BIOS_ROM_BASE           0xffe00000
+#define BIOS_ROM_END            0xffffffff
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
@@ -93,7 +96,7 @@ extern void e820_setup_gap(void);
 extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
                         unsigned long start_addr, unsigned long long end_addr);
 struct setup_data;
-extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+extern void parse_e820_ext(struct setup_data *data);
 
 #if defined(CONFIG_X86_64) || \
         (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
@@ -112,23 +115,13 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 }
 #endif
 
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-#include <linux/early_res.h>
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
-                                  unsigned long start_pfn,
-                                  unsigned long last_pfn,
-                                  unsigned long *ei_startpfn,
-                                  unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-                                         unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+void memblock_x86_fill(void);
+void memblock_find_dma_reserve(void);
+
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7f9926..7093e4a6a0bc 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,7 +90,8 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
+extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 5d07dea2ebb8..3b0d7ef959b8 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -17,22 +17,14 @@ BUILD_INTERRUPT(pull_timers_interrupt,PULL_TIMERS_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
-BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
-                 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
-                 smp_invalidate_interrupt)
+.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+        16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+.if NUM_INVALIDATE_TLB_VECTORS > \idx
+BUILD_INTERRUPT3(invalidate_interrupt\idx,
+                 (INVALIDATE_TLB_VECTOR_START)+\idx,
+                 smp_invalidate_interrupt)
+.endif
+.endr
 #endif
 
 BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
@@ -50,8 +42,8 @@ BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
-#ifdef CONFIG_PERF_EVENTS
-BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
+#ifdef CONFIG_IRQ_WORK
+BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR)
 #endif
 
 #ifdef CONFIG_X86_THERMAL_VECTOR
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index d07b44f7d1dc..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.
@@ -214,5 +218,20 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
         BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
         return __virt_to_fix(vaddr);
 }
+
+/* Return an pointer with offset calculated */
+static __always_inline unsigned long
+__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
+{
+        __set_fixmap(idx, phys, flags);
+        return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1));
+}
+
+#define set_fixmap_offset(idx, phys)                    \
+        __set_fixmap_offset(idx, phys, PAGE_KERNEL)
+
+#define set_fixmap_offset_nocache(idx, phys)                    \
+        __set_fixmap_offset(idx, phys, PAGE_KERNEL_NOCACHE)
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 06850a7194e1..2c6fc9e62812 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -7,14 +7,12 @@
    frame pointer later */
 #ifdef CONFIG_FRAME_POINTER
         .macro FRAME
-        pushl %ebp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebp
         CFI_REL_OFFSET ebp,0
         movl %esp,%ebp
         .endm
         .macro ENDFRAME
-        popl %ebp
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %ebp
         CFI_RESTORE ebp
         .endm
 #else
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c2278be0..268c783ab1c0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -38,11 +38,10 @@ extern void mcount(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
         /*
-         * call mcount is "e8 <4 byte offset>"
-         * The addr points to the 4 byte offset and the caller of this
-         * function wants the pointer to e8. Simply subtract one.
+         * addr is the address of the mcount call instruction.
+         * recordmcount does the necessary offset calculation.
          */
-        return addr - 1;
+        return addr;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 1f11ce44e956..d09bb03653f0 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -37,7 +37,7 @@
                        "+m" (*uaddr), "=&r" (tem)               \
                      : "r" (oparg), "i" (-EFAULT), "1" (0))
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
         int op = (encoded_op >> 28) & 7;
         int cmp = (encoded_op >> 24) & 15;
@@ -48,7 +48,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
         if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
                 oparg = 1 << oparg;
 
-        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
                 return -EFAULT;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
@@ -109,9 +109,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
         return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-                                                int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+                                                u32 oldval, u32 newval)
 {
+        int ret = 0;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
         /* Real i386 machines have no cmpxchg instruction */
@@ -119,21 +120,22 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
                 return -ENOSYS;
 #endif
 
-        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
                 return -EFAULT;
 
-        asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
+        asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
                      "2:\t.section .fixup, \"ax\"\n"
-                     "3:\tmov     %2, %0\n"
+                     "3:\tmov     %3, %0\n"
                      "\tjmp     2b\n"
                      "\t.previous\n"
                      _ASM_EXTABLE(1b, 3b)
-                     : "=a" (oldval), "+m" (*uaddr)
-                     : "i" (-EFAULT), "r" (newval), "0" (oldval)
+                     : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
+                     : "i" (-EFAULT), "r" (newval), "1" (oldval)
                      : "memory"
         );
 
-        return oldval;
+        *uval = oldval;
+        return ret;
 }
 
 #endif
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 4ac5b0f33fc1..156cd5d18d2a 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -17,6 +17,7 @@ extern int fix_aperture;
 #define GARTEN          (1<<0)
 #define DISGARTCPU      (1<<4)
 #define DISGARTIO       (1<<5)
+#define DISTLBWALKPRB   (1<<6)
 
 /* GART cache control register bits. */
 #define INVGART         (1<<0)
@@ -27,7 +28,6 @@ extern int fix_aperture;
 #define AMD64_GARTAPERTUREBASE  0x94
 #define AMD64_GARTTABLEBASE     0x98
 #define AMD64_GARTCACHECTL      0x9c
-#define AMD64_GARTEN            (1<<0)
 
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
@@ -37,7 +37,7 @@ extern int gart_iommu_aperture_disabled;
 extern void early_gart_iommu_check(void);
 extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
+extern int gart_iommu_hole_init(void);
 
 #else
 #define gart_iommu_aperture            0
@@ -50,28 +50,42 @@ static inline void early_gart_iommu_check(void)
 static inline void gart_parse_options(char *options)
 {
 }
-static inline void gart_iommu_hole_init(void)
+static inline int gart_iommu_hole_init(void)
 {
+        return -ENODEV;
 }
 #endif
 
 extern int agp_amd64_init(void);
 
+static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
+{
+        u32 ctl;
+
+        /*
+         * Don't enable translation but enable GART IO and CPU accesses.
+         * Also, set DISTLBWALKPRB since GART tables memory is UC.
+         */
+        ctl = order << 1;
+
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
         u32 tmp, ctl;
 
-        /* address of the mappings table */
-        addr >>= 12;
-        tmp = (u32) addr<<4;
-        tmp &= ~0xf;
-        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
-        /* Enable GART translation for this hammer. */
-        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-        ctl |= GARTEN;
-        ctl &= ~(DISGARTCPU | DISGARTIO);
-        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+        /* address of the mappings table */
+        addr >>= 12;
+        tmp = (u32) addr<<4;
+        tmp &= ~0xf;
+        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+        /* Enable GART translation for this hammer. */
+        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+        ctl |= GARTEN | DISTLBWALKPRB;
+        ctl &= ~(DISGARTCPU | DISGARTIO);
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
 static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
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/hardirq.h b/arch/x86/include/asm/hardirq.h
index aeab29aee617..55e4de613f0e 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,7 +14,7 @@ typedef struct {
 #endif
         unsigned int x86_platform_ipis; /* arch dependent */
         unsigned int apic_perf_irqs;
-        unsigned int apic_pending_irqs;
+        unsigned int apic_irq_work_irqs;
 #ifdef CONFIG_SMP
         unsigned int irq_resched_count;
         unsigned int irq_call_count;
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 8caac76ac324..3bd04022fd0c 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -59,11 +59,12 @@ extern void kunmap_high(struct page *page);
 
 void *kmap(struct page *page);
 void kunmap(struct page *page);
-void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
-void *kmap_atomic(struct page *page, enum km_type type);
-void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type);
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
-void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+void *__kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic_pfn(unsigned long pfn);
+void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()     do { } while (0)
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1d5c08a1bdfd..2c392d663dce 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,10 +74,12 @@ extern void hpet_disable(void);
 extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
 extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index c17411503f28..c490d89a9b7b 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,7 +29,7 @@
 extern void apic_timer_interrupt(void);
 extern void x86_platform_ipi(void);
 extern void error_interrupt(void);
-extern void perf_pending_interrupt(void);
+extern void irq_work_interrupt(void);
 
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
@@ -45,6 +45,30 @@ extern void invalidate_interrupt4(void);
 extern void invalidate_interrupt5(void);
 extern void invalidate_interrupt6(void);
 extern void invalidate_interrupt7(void);
+extern void invalidate_interrupt8(void);
+extern void invalidate_interrupt9(void);
+extern void invalidate_interrupt10(void);
+extern void invalidate_interrupt11(void);
+extern void invalidate_interrupt12(void);
+extern void invalidate_interrupt13(void);
+extern void invalidate_interrupt14(void);
+extern void invalidate_interrupt15(void);
+extern void invalidate_interrupt16(void);
+extern void invalidate_interrupt17(void);
+extern void invalidate_interrupt18(void);
+extern void invalidate_interrupt19(void);
+extern void invalidate_interrupt20(void);
+extern void invalidate_interrupt21(void);
+extern void invalidate_interrupt22(void);
+extern void invalidate_interrupt23(void);
+extern void invalidate_interrupt24(void);
+extern void invalidate_interrupt25(void);
+extern void invalidate_interrupt26(void);
+extern void invalidate_interrupt27(void);
+extern void invalidate_interrupt28(void);
+extern void invalidate_interrupt29(void);
+extern void invalidate_interrupt30(void);
+extern void invalidate_interrupt31(void);
 
 extern void irq_move_cleanup_interrupt(void);
 extern void reboot_interrupt(void);
@@ -80,6 +104,13 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
         irq_attr->polarity      = polarity;
 }
 
+struct irq_2_iommu {
+        struct intel_iommu *iommu;
+        u16 irte_index;
+        u16 sub_handle;
+        u8  irte_mask;
+};
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -91,15 +122,17 @@ struct irq_cfg {
         cpumask_var_t           old_domain;
         u8                      vector;
         u8                      move_in_progress : 1;
+#ifdef CONFIG_INTR_REMAP
+        struct irq_2_iommu      irq_2_iommu;
+#endif
 };
 
-extern struct irq_cfg *irq_cfg(unsigned int);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
-                                      unsigned int *dest_id);
+struct irq_data;
+int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
+                          unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/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 a73a8d5a5e69..c9e09ea05644 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -55,6 +55,12 @@ extern int save_i387_xstate_ia32(void __user *buf);
 extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
 #define X87_FSW_ES (1 << 7)     /* Exception Summary */
 
 static __always_inline __pure bool use_xsaveopt(void)
@@ -67,6 +73,11 @@ static __always_inline __pure bool use_xsave(void)
         return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
+static __always_inline __pure bool use_fxsr(void)
+{
+        return static_cpu_has(X86_FEATURE_FXSR);
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -77,20 +88,13 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-        asm volatile("1: fwait\n"
-                     "2:\n"
-                     _ASM_EXTABLE(1b, 2b));
-}
-
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
         int err;
 
-        asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
+        /* 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"
@@ -98,44 +102,21 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
                      ".previous\n"
                      _ASM_EXTABLE(1b, 3b)
                      : [err] "=r" (err)
-#if 0 /* See comment in fxsave() below. */
-                     : [fx] "r" (fx), "m" (*fx), "0" (0));
+                     : [fx] "m" (*fx), "0" (0));
 #else
-                     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
+        asm volatile("1:  rex64/fxrstor (%[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] "R" (fx), "m" (*fx), "0" (0));
 #endif
         return err;
 }
 
-/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
-   is pending. Clear the x87 state here by setting it to fixed
-   values. The kernel data segment can be sometimes 0 and sometimes
-   new user value. Both should be ok.
-   Use the PDA as safe address because it should be already in L1. */
-static inline void fpu_clear(struct fpu *fpu)
-{
-        struct xsave_struct *xstate = &fpu->state->xsave;
-        struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-        /*
-         * xsave header may indicate the init state of the FP.
-         */
-        if (use_xsave() &&
-            !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-                return;
-
-        if (unlikely(fx->swd & X87_FSW_ES))
-                asm volatile("fnclex");
-        alternative_input(ASM_NOP8 ASM_NOP2,
-                          "    emms\n"          /* clear stack tags */
-                          "    fildl %%gs:0",   /* load to clear state */
-                          X86_FEATURE_FXSAVE_LEAK);
-}
-
-static inline void clear_fpu_state(struct task_struct *tsk)
-{
-        fpu_clear(&tsk->thread.fpu);
-}
-
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
         int err;
@@ -149,6 +130,18 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
         if (unlikely(err))
                 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"
@@ -157,10 +150,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
                      ".previous\n"
                      _ASM_EXTABLE(1b, 3b)
                      : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in fxsave() below. */
-                     : [fx] "r" (fx), "0" (0));
-#else
-                     : [fx] "cdaSDb" (fx), "0" (0));
+                     : [fx] "R" (fx), "0" (0));
 #endif
         if (unlikely(err) &&
             __clear_user(fx, sizeof(struct i387_fxsave_struct)))
@@ -175,56 +165,29 @@ static inline void fpu_fxsave(struct fpu *fpu)
            uses any extended registers for addressing, a second REX prefix
            will be generated (to the assembler, rex64 followed by semicolon
            is a separate instruction), and hence the 64-bitness is lost. */
-#if 0
+
+#ifdef CONFIG_AS_FXSAVEQ
         /* Using "fxsaveq %0" would be the ideal choice, but is only supported
            starting with gas 2.16. */
         __asm__ __volatile__("fxsaveq %0"
                              : "=m" (fpu->state->fxsave));
-#elif 0
+#else
         /* Using, as a workaround, the properly prefixed form below isn't
            accepted by any binutils version so far released, complaining that
            the same type of prefix is used twice if an extended register is
-           needed for addressing (fix submitted to mainline 2005-11-21). */
-        __asm__ __volatile__("rex64/fxsave %0"
-                             : "=m" (fpu->state->fxsave));
-#else
-        /* This, however, we can work around by forcing the compiler to select
+           needed for addressing (fix submitted to mainline 2005-11-21).
+        asm volatile("rex64/fxsave %0"
+                     : "=m" (fpu->state->fxsave));
+           This, however, we can work around by forcing the compiler to select
            an addressing mode that doesn't require extended registers. */
-        __asm__ __volatile__("rex64/fxsave (%1)"
-                             : "=m" (fpu->state->fxsave)
-                             : "cdaSDb" (&fpu->state->fxsave));
+        asm volatile("rex64/fxsave (%[fx])"
+                     : "=m" (fpu->state->fxsave)
+                     : [fx] "R" (&fpu->state->fxsave));
 #endif
 }
 
-static inline void fpu_save_init(struct fpu *fpu)
-{
-        if (use_xsave())
-                fpu_xsave(fpu);
-        else
-                fpu_fxsave(fpu);
-
-        fpu_clear(fpu);
-}
-
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-        fpu_save_init(&tsk->thread.fpu);
-        task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
 #else  /* CONFIG_X86_32 */
 
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-static inline void tolerant_fwait(void)
-{
-        asm volatile("fnclex ; fwait");
-}
-
 /* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
@@ -241,6 +204,14 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
         return 0;
 }
 
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+        asm volatile("fxsave %[fx]"
+                     : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif  /* CONFIG_X86_64 */
+
 /* We need a safe address that is cheap to find and that is already
    in L1 during context switch. The best choices are unfortunately
    different for UP and SMP */
@@ -256,47 +227,33 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 static inline void fpu_save_init(struct fpu *fpu)
 {
         if (use_xsave()) {
-                struct xsave_struct *xstate = &fpu->state->xsave;
-                struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
                 fpu_xsave(fpu);
 
                 /*
                  * xsave header may indicate the init state of the FP.
                  */
-                if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-                        goto end;
-
-                if (unlikely(fx->swd & X87_FSW_ES))
-                        asm volatile("fnclex");
-
-                /*
-                 * we can do a simple return here or be paranoid :)
-                 */
-                goto clear_state;
+                if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+                        return;
+        } else if (use_fxsr()) {
+                fpu_fxsave(fpu);
+        } else {
+                asm volatile("fnsave %[fx]; fwait"
+                             : [fx] "=m" (fpu->state->fsave));
+                return;
         }
 
-        /* Use more nops than strictly needed in case the compiler
-           varies code */
-        alternative_input(
-                "fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
-                "fxsave %[fx]\n"
-                "bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
-                X86_FEATURE_FXSR,
-                [fx] "m" (fpu->state->fxsave),
-                [fsw] "m" (fpu->state->fxsave.swd) : "memory");
-clear_state:
+        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+                asm volatile("fnclex");
+
         /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
            is pending.  Clear the x87 state here by setting it to fixed
            values. safe_address is a random variable that should be in L1 */
         alternative_input(
-                GENERIC_NOP8 GENERIC_NOP2,
+                ASM_NOP8 ASM_NOP2,
                 "emms\n\t"              /* clear stack tags */
-                "fildl %[addr]",        /* set F?P to defined value */
+                "fildl %P[addr]",       /* set F?P to defined value */
                 X86_FEATURE_FXSAVE_LEAK,
                 [addr] "m" (safe_address));
-end:
-        ;
 }
 
 static inline void __save_init_fpu(struct task_struct *tsk)
@@ -305,9 +262,6 @@ static inline void __save_init_fpu(struct task_struct *tsk)
         task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
-
-#endif  /* CONFIG_X86_64 */
-
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
 {
         return fxrstor_checking(&fpu->state->fxsave);
@@ -344,7 +298,10 @@ static inline void __unlazy_fpu(struct task_struct *tsk)
 static inline void __clear_fpu(struct task_struct *tsk)
 {
         if (task_thread_info(tsk)->status & TS_USEDFPU) {
-                tolerant_fwait();
+                /* Ignore delayed exceptions from user space */
+                asm volatile("1: fwait\n"
+                             "2:\n"
+                             _ASM_EXTABLE(1b, 2b));
                 task_thread_info(tsk)->status &= ~TS_USEDFPU;
                 stts();
         }
@@ -405,19 +362,6 @@ static inline void irq_ts_restore(int TS_state)
                 stts();
 }
 
-#ifdef CONFIG_X86_64
-
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-        __save_init_fpu(tsk);
-        stts();
-}
-
-#define unlazy_fpu      __unlazy_fpu
-#define clear_fpu       __clear_fpu
-
-#else  /* CONFIG_X86_32 */
-
 /*
  * These disable preemption on their own and are safe
  */
@@ -443,8 +387,6 @@ static inline void clear_fpu(struct task_struct *tsk)
         preempt_enable();
 }
 
-#endif  /* CONFIG_X86_64 */
-
 /*
  * i387 state interaction
  */
@@ -508,7 +450,4 @@ extern void fpu_finit(struct fpu *fpu);
 
 #endif /* __ASSEMBLY__ */
 
-#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
-#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5
-
 #endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
index fc1f579fb965..65aaa91d5850 100644
--- a/arch/x86/include/asm/i8253.h
+++ b/arch/x86/include/asm/i8253.h
@@ -6,6 +6,8 @@
 #define PIT_CH0                 0x40
 #define PIT_CH2                 0x42
 
+#define PIT_LATCH       LATCH
+
 extern raw_spinlock_t i8253_lock;
 
 extern struct clock_event_device *global_clock_event;
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1655147646aa..a20365953bf8 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -55,6 +55,8 @@ extern struct irq_chip i8259A_chip;
 struct legacy_pic {
         int nr_legacy_irqs;
         struct irq_chip *chip;
+        void (*mask)(unsigned int irq);
+        void (*unmask)(unsigned int irq);
         void (*mask_all)(void);
         void (*restore_mask)(void);
         void (*init)(int auto_eoi);
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 38d87379e270..f49253d75710 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -16,6 +16,6 @@ static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
-void c1e_remove_cpu(int cpu);
+void amd_e400_remove_cpu(int cpu);
 
 #endif /* _ASM_X86_IDLE_H */
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 36fb1a6a5109..8dbe353e41e1 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -11,8 +11,8 @@ kernel_physical_mapping_init(unsigned long start,
                              unsigned long page_size_mask);
 
 
-extern unsigned long __initdata e820_table_start;
-extern unsigned long __meminitdata e820_table_end;
-extern unsigned long __meminitdata e820_table_top;
+extern unsigned long __initdata pgt_buf_start;
+extern unsigned long __meminitdata pgt_buf_end;
+extern unsigned long __meminitdata pgt_buf_top;
 
 #endif /* _ASM_X86_INIT_32_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e9776123..d02804d650c4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -38,9 +38,10 @@
 
 #include <linux/string.h>
 #include <linux/compiler.h>
-#include <asm-generic/int-ll64.h>
 #include <asm/page.h>
 
+#include <xen/xen.h>
+
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
 { type ret; asm volatile("mov" size " %1,%0":reg (ret) \
@@ -85,27 +86,6 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
 
-#else
-
-static inline __u64 readq(const volatile void __iomem *addr)
-{
-        const volatile u32 __iomem *p = addr;
-        u32 low, high;
-
-        low = readl(p);
-        high = readl(p + 1);
-
-        return low + ((u64)high << 32);
-}
-
-static inline void writeq(__u64 val, volatile void __iomem *addr)
-{
-        writel(val, addr);
-        writel(val >> 32, addr+4);
-}
-
-#endif
-
 #define readq_relaxed(a)        readq(a)
 
 #define __raw_readq(a)          readq(a)
@@ -115,6 +95,8 @@ static inline void writeq(__u64 val, volatile void __iomem *addr)
 #define readq                   readq
 #define writeq                  writeq
 
+#endif
+
 /**
  *      virt_to_phys    -       map virtual addresses to physical
  *      @address: address to remap
@@ -206,6 +188,7 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 
 extern void iounmap(volatile void __iomem *addr);
 
+extern void set_iounmap_nonlazy(void);
 
 #ifdef __KERNEL__
 
@@ -348,6 +331,18 @@ extern void __iomem *early_memremap(resource_size_t phys_addr,
                                     unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void fixup_early_ioremap(void);
+extern bool is_early_ioremap_ptep(pte_t *ptep);
+
+#ifdef CONFIG_XEN
+struct bio_vec;
+
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+                                      const struct bio_vec *vec2);
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)                               \
+        (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&                         \
+         (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+#endif  /* CONFIG_XEN */
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb87c2f..690d1cc9a877 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -63,17 +63,6 @@ union IO_APIC_reg_03 {
         } __attribute__ ((packed)) bits;
 };
 
-enum ioapic_irq_destination_types {
-        dest_Fixed = 0,
-        dest_LowestPrio = 1,
-        dest_SMI = 2,
-        dest__reserved_1 = 3,
-        dest_NMI = 4,
-        dest_INIT = 5,
-        dest__reserved_2 = 6,
-        dest_ExtINT = 7
-};
-
 struct IO_APIC_route_entry {
         __u32   vector          :  8,
                 delivery_mode   :  3,   /* 000: FIXED
@@ -106,18 +95,22 @@ struct IR_IO_APIC_route_entry {
                 index           : 15;
 } __attribute__ ((packed));
 
+#define IOAPIC_AUTO     -1
+#define IOAPIC_EDGE     0
+#define IOAPIC_LEVEL    1
+
 #ifdef CONFIG_X86_IO_APIC
 
 /*
  * # of IO-APICs and # of IRQ routing registers
  */
 extern int nr_ioapics;
-extern int nr_ioapic_registers[MAX_IO_APICS];
 
-#define MP_MAX_IOAPIC_PIN 127
+extern int mpc_ioapic_id(int ioapic);
+extern unsigned int mpc_ioapic_addr(int ioapic);
+extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
 
-/* I/O APIC entries */
-extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
+#define MP_MAX_IOAPIC_PIN 127
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
@@ -150,33 +143,23 @@ extern int timer_through_8259;
 #define io_apic_assign_pci_irqs \
         (mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
 
-extern u8 io_apic_unique_id(u8 id);
-extern int io_apic_get_unique_id(int ioapic, int apic_id);
-extern int io_apic_get_version(int ioapic);
-extern int io_apic_get_redir_entries(int ioapic);
-
 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);
-extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
-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);
+int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
-extern void probe_nr_irqs_gsi(void);
+extern int save_ioapic_entries(void);
+extern void mask_ioapic_entries(void);
+extern int restore_ioapic_entries(void);
+
+extern int get_nr_irqs_gsi(void);
 
-extern int setup_ioapic_entry(int apic, int irq,
-                              struct IO_APIC_route_entry *entry,
-                              unsigned int destination, int trigger,
-                              int polarity, int vector, int pin);
-extern void ioapic_write_entry(int apic, int pin,
-                               struct IO_APIC_route_entry e);
 extern void setup_ioapic_ids_from_mpc(void);
+extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
 struct mp_ioapic_gsi{
         u32 gsi_base;
@@ -189,20 +172,37 @@ 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);
+
+extern void disable_ioapic_support(void);
+
 #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; }
 
 struct io_apic_irq_attr;
 static inline int io_apic_set_pci_routing(struct device *dev, int irq,
                  struct io_apic_irq_attr *irq_attr) { return 0; }
+
+static inline int save_ioapic_entries(void)
+{
+        return -ENOMEM;
+}
+
+static inline void mask_ioapic_entries(void) { }
+static inline int restore_ioapic_entries(void)
+{
+        return -ENOMEM;
+}
+
+static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void disable_ioapic_support(void) { }
 #endif
 
 #endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index c4191b3b7056..363e33eb6ec1 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -27,10 +27,10 @@
 #include <asm/tlbflush.h>
 
 void __iomem *
-iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 
 void
-iounmap_atomic(void __iomem *kvaddr, enum km_type type);
+iounmap_atomic(void __iomem *kvaddr);
 
 int
 iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
new file mode 100644
index 000000000000..f229b13a5f30
--- /dev/null
+++ b/arch/x86/include/asm/iommu_table.h
@@ -0,0 +1,100 @@
+#ifndef _ASM_X86_IOMMU_TABLE_H
+#define _ASM_X86_IOMMU_TABLE_H
+
+#include <asm/swiotlb.h>
+
+/*
+ * History lesson:
+ * The execution chain of IOMMUs in 2.6.36 looks as so:
+ *
+ *            [xen-swiotlb]
+ *                 |
+ *         +----[swiotlb *]--+
+ *        /         |         \
+ *       /          |          \
+ *    [GART]     [Calgary]  [Intel VT-d]
+ *     /
+ *    /
+ * [AMD-Vi]
+ *
+ * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
+ * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
+ * Also it would surreptitiously initialize set the swiotlb=1 if there were
+ * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
+ * flag would be turned off by all IOMMUs except the Calgary one.
+ *
+ * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
+ * to be built by defining who we depend on.
+ *
+ * And all that needs to be done is to use one of the macros in the IOMMU
+ * and the pci-dma.c will take care of the rest.
+ */
+
+struct iommu_table_entry {
+        initcall_t      detect;
+        initcall_t      depend;
+        void            (*early_init)(void); /* No memory allocate available. */
+        void            (*late_init)(void); /* Yes, can allocate memory. */
+#define IOMMU_FINISH_IF_DETECTED (1<<0)
+#define IOMMU_DETECTED           (1<<1)
+        int             flags;
+};
+/*
+ * Macro fills out an entry in the .iommu_table that is equivalent
+ * to the fields that 'struct iommu_table_entry' has. The entries
+ * that are put in the .iommu_table section are not put in any order
+ * hence during boot-time we will have to resort them based on
+ * dependency. */
+
+
+#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
+        static const struct iommu_table_entry const                     \
+                __iommu_entry_##_detect __used                          \
+        __attribute__ ((unused, __section__(".iommu_table"),            \
+                        aligned((sizeof(void *)))))     \
+        = {_detect, _depend, _early_init, _late_init,                   \
+           _finish ? IOMMU_FINISH_IF_DETECTED : 0}
+/*
+ * The simplest IOMMU definition. Provide the detection routine
+ * and it will be run after the SWIOTLB and the other IOMMUs
+ * that utilize this macro. If the IOMMU is detected (ie, the
+ * detect routine returns a positive value), the other IOMMUs
+ * are also checked. You can use IOMMU_INIT_POST_FINISH if you prefer
+ * to stop detecting the other IOMMUs after yours has been detected.
+ */
+#define IOMMU_INIT_POST(_detect)                                        \
+        __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 0)
+
+#define IOMMU_INIT_POST_FINISH(detect)                                  \
+        __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 1)
+
+/*
+ * A more sophisticated version of IOMMU_INIT. This variant requires:
+ *  a). A detection routine function.
+ *  b). The name of the detection routine we depend on to get called
+ *      before us.
+ *  c). The init routine which gets called if the detection routine
+ *      returns a positive value from the pci_iommu_alloc. This means
+ *      no presence of a memory allocator.
+ *  d). Similar to the 'init', except that this gets called from pci_iommu_init
+ *      where we do have a memory allocator.
+ *
+ * The standard vs the _FINISH differs in that the _FINISH variant will
+ * continue detecting other IOMMUs in the call list after the
+ * the detection routine returns a positive number. The _FINISH will
+ * stop the execution chain. Both will still call the 'init' and
+ * 'late_init' functions if they are set.
+ */
+#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)          \
+        __IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
+
+#define IOMMU_INIT(_detect, _depend, _init, _late_init)                 \
+        __IOMMU_INIT(_detect, _depend, _init, _late_init, 0)
+
+void sort_iommu_table(struct iommu_table_entry *start,
+                      struct iommu_table_entry *finish);
+
+void check_iommu_entries(struct iommu_table_entry *start,
+                         struct iommu_table_entry *finish);
+
+#endif /* _ASM_X86_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index 0b7228268a63..615fa9061b57 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -123,10 +123,6 @@ extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
                                                  int vector);
 extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
                                                          int vector);
-extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
-                                                         int vector);
-extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
-                                                         int vector);
 
 /* Avoid include hell */
 #define NMI_VECTOR 0x02
@@ -150,6 +146,10 @@ static inline void __default_local_send_IPI_all(int vector)
 }
 
 #ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+                                                         int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+                                                         int vector);
 extern void default_send_IPI_mask_logical(const struct cpumask *mask,
                                                  int vector);
 extern void default_send_IPI_allbutself(int vector);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380b6ef8..ba870bb6dd8e 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -15,22 +15,14 @@ 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_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
 #else
 # define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
 #endif
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h
new file mode 100644
index 000000000000..423bbbddf36d
--- /dev/null
+++ b/arch/x86/include/asm/irq_controller.h
@@ -0,0 +1,12 @@
+#ifndef __IRQ_CONTROLLER__
+#define __IRQ_CONTROLLER__
+
+struct irq_domain {
+        int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize,
+                        u32 *out_hwirq, u32 *out_type);
+        void *priv;
+        struct device_node *controller;
+        struct list_head l;
+};
+
+#endif
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index f275e2244505..1c23360fb2d8 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,4 +3,39 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
+#ifdef CONFIG_INTR_REMAP
+static inline void prepare_irte(struct irte *irte, int vector,
+                                unsigned int dest)
+{
+        memset(irte, 0, sizeof(*irte));
+
+        irte->present = 1;
+        irte->dst_mode = apic->irq_dest_mode;
+        /*
+         * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+         * actual level or edge trigger will be setup in the IO-APIC
+         * RTE. This will help simplify level triggered irq migration.
+         * For more details, see the comments (in io_apic.c) explainig IO-APIC
+         * irq migration in the presence of interrupt-remapping.
+        */
+        irte->trigger_mode = 0;
+        irte->dlvry_mode = apic->irq_delivery_mode;
+        irte->vector = vector;
+        irte->dest_id = IRTE_DEST(dest);
+        irte->redir_hint = 1;
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+        return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+        return false;
+}
+#endif
+
 #endif  /* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6143ebeeebfa..99a44cf98453 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_IRQ_VECTORS_H
 #define _ASM_X86_IRQ_VECTORS_H
 
+#include <linux/threads.h>
 /*
  * Linux IRQ vector layout.
  *
@@ -16,8 +17,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... 237 : device interrupts
- *  Vectors 238 ... 255 : special interrupts
+ *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts
+ *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *
@@ -96,42 +97,50 @@
 #define THRESHOLD_APIC_VECTOR           0xf9
 #define REBOOT_VECTOR                   0xf8
 
-/* f0-f7 used for spreading out TLB flushes: */
-#define INVALIDATE_TLB_VECTOR_END       0xf7
-#define INVALIDATE_TLB_VECTOR_START     0xf0
-#define NUM_INVALIDATE_TLB_VECTORS         8
-
 /*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
+ * Generic system vector for platform specific use
  */
-#define LOCAL_TIMER_VECTOR              0xef
+#define X86_PLATFORM_IPI_VECTOR         0xf7
 
 /*
- * LITMUS^RT pull timers IRQ vector
+ * IRQ work vector:
  */
-#define PULL_TIMERS_VECTOR              0xee
+#define IRQ_WORK_VECTOR                 0xf6
+
+#define UV_BAU_MESSAGE                  0xf5
 
 /*
- * Generic system vector for platform specific use
+ * Self IPI vector for machine checks
  */
-#define X86_PLATFORM_IPI_VECTOR         0xed
+#define MCE_SELF_VECTOR                 0xf4
+
+/* Xen vector callback to receive events in a HVM domain */
+#define XEN_HVM_EVTCHN_CALLBACK         0xf3
 
 /*
- * Performance monitoring pending work vector:
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
  */
-#define LOCAL_PENDING_VECTOR            0xec
+#define LOCAL_TIMER_VECTOR              0xef
 
-#define UV_BAU_MESSAGE                  0xea
+/* up to 32 vectors used for spreading out TLB flushes: */
+#if NR_CPUS <= 32
+# define NUM_INVALIDATE_TLB_VECTORS     (NR_CPUS)
+#else
+# define NUM_INVALIDATE_TLB_VECTORS     (32)
+#endif
+
+#define INVALIDATE_TLB_VECTOR_END       (0xee)
+#define INVALIDATE_TLB_VECTOR_START     \
+        (INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1)
 
 /*
- * Self IPI vector for machine checks
+ * LITMUS^RT pull timers IRQ vector
+ * Make sure it's below the above max 32 vectors.
  */
-#define MCE_SELF_VECTOR                 0xeb
+#define PULL_TIMERS_VECTOR              0xce
 
-/* Xen vector callback to receive events in a HVM domain */
-#define XEN_HVM_EVTCHN_CALLBACK         0xe9
 
 #define NR_VECTORS                       256
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9e2b952f810a..5745ce8bf108 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -61,22 +61,22 @@ static inline void native_halt(void)
 #else
 #ifndef __ASSEMBLY__
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
         return native_save_fl();
 }
 
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline void arch_local_irq_restore(unsigned long flags)
 {
         native_restore_fl(flags);
 }
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
         native_irq_disable();
 }
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
         native_irq_enable();
 }
@@ -85,7 +85,7 @@ static inline void raw_local_irq_enable(void)
  * Used in the idle loop; sti takes one instruction cycle
  * to complete:
  */
-static inline void raw_safe_halt(void)
+static inline void arch_safe_halt(void)
 {
         native_safe_halt();
 }
@@ -102,12 +102,10 @@ static inline void halt(void)
 /*
  * For spinlocks, etc:
  */
-static inline unsigned long __raw_local_irq_save(void)
+static inline unsigned long arch_local_irq_save(void)
 {
-        unsigned long flags = __raw_local_save_flags();
-
-        raw_local_irq_disable();
-
+        unsigned long flags = arch_local_save_flags();
+        arch_local_irq_disable();
         return flags;
 }
 #else
@@ -153,22 +151,16 @@ static inline unsigned long __raw_local_irq_save(void)
 #endif /* CONFIG_PARAVIRT */
 
 #ifndef __ASSEMBLY__
-#define raw_local_save_flags(flags)                             \
-        do { (flags) = __raw_local_save_flags(); } while (0)
-
-#define raw_local_irq_save(flags)                               \
-        do { (flags) = __raw_local_irq_save(); } while (0)
-
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
         return !(flags & X86_EFLAGS_IF);
 }
 
-static inline int raw_irqs_disabled(void)
+static inline int arch_irqs_disabled(void)
 {
-        unsigned long flags = __raw_local_save_flags();
+        unsigned long flags = arch_local_save_flags();
 
-        return raw_irqs_disabled_flags(flags);
+        return arch_irqs_disabled_flags(flags);
 }
 
 #else
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
new file mode 100644
index 000000000000..a32b18ce6ead
--- /dev/null
+++ b/arch/x86/include/asm/jump_label.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_X86_JUMP_LABEL_H
+#define _ASM_X86_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/nops.h>
+#include <asm/asm.h>
+
+#define JUMP_LABEL_NOP_SIZE 5
+
+#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+        asm goto("1:"
+                JUMP_LABEL_INITIAL_NOP
+                ".pushsection __jump_table,  \"aw\" \n\t"
+                _ASM_ALIGN "\n\t"
+                _ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+                ".popsection \n\t"
+                : :  "i" (key) : : l_yes);
+        return false;
+l_yes:
+        return true;
+}
+
+#endif /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+typedef u64 jump_label_t;
+#else
+typedef u32 jump_label_t;
+#endif
+
+struct jump_entry {
+        jump_label_t code;
+        jump_label_t target;
+        jump_label_t key;
+};
+
+#endif
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
deleted file mode 100644
index af00bd1d2089..000000000000
--- a/arch/x86/include/asm/k8.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef _ASM_X86_K8_H
-#define _ASM_X86_K8_H
-
-#include <linux/pci.h>
-
-extern struct pci_device_id k8_nb_ids[];
-struct bootnode;
-
-extern int early_is_k8_nb(u32 value);
-extern struct pci_dev **k8_northbridges;
-extern int num_k8_northbridges;
-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);
-
-#ifdef CONFIG_K8_NB
-extern int num_k8_northbridges;
-
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
-{
-        return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
-}
-
-#else
-#define num_k8_northbridges 0
-
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
-{
-        return NULL;
-}
-#endif
-
-
-#endif /* _ASM_X86_K8_H */
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 5bdfca86581b..fe2cc6e105fa 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -13,12 +13,10 @@ enum die_val {
         DIE_PANIC,
         DIE_NMI,
         DIE_DIE,
-        DIE_NMIWATCHDOG,
         DIE_KERNELDEBUG,
         DIE_TRAP,
         DIE_GPF,
         DIE_CALL,
-        DIE_NMI_IPI,
         DIE_PAGE_FAULT,
         DIE_NMIUNKNOWN,
 };
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
index 396f5b5fc4d7..77e95f54570a 100644
--- a/arch/x86/include/asm/kgdb.h
+++ b/arch/x86/include/asm/kgdb.h
@@ -77,6 +77,7 @@ static inline void arch_kgdb_breakpoint(void)
 }
 #define BREAK_INSTR_SIZE        1
 #define CACHE_FLUSH_IS_SAFE     1
+#define GDB_ADJUSTS_BREAK_OFFSET
 
 extern int kgdb_ll_trap(int cmd, const char *str,
                         struct pt_regs *regs, long err, int trap, int sig);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1f99ecfc48e1..0049211959c0 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -14,6 +14,34 @@
 #include <asm/desc_defs.h>
 
 struct x86_emulate_ctxt;
+enum x86_intercept;
+enum x86_intercept_stage;
+
+struct x86_exception {
+        u8 vector;
+        bool error_code_valid;
+        u16 error_code;
+        bool nested_page_fault;
+        u64 address; /* cr2 or nested page fault gpa */
+};
+
+/*
+ * This struct is used to carry enough information from the instruction
+ * decoder to main KVM so that a decision can be made whether the
+ * instruction needs to be intercepted or not.
+ */
+struct x86_instruction_info {
+        u8  intercept;          /* which intercept                      */
+        u8  rep_prefix;         /* rep prefix?                          */
+        u8  modrm_mod;          /* mod part of modrm                    */
+        u8  modrm_reg;          /* index of register used               */
+        u8  modrm_rm;           /* rm part of modrm                     */
+        u64 src_val;            /* value of source operand              */
+        u8  src_bytes;          /* size of source operand               */
+        u8  dst_bytes;          /* size of destination operand          */
+        u8  ad_bytes;           /* size of src/dst address              */
+        u64 next_rip;           /* rip following the instruction        */
+};
 
 /*
  * x86_emulate_ops:
@@ -54,6 +82,7 @@ struct x86_emulate_ctxt;
 #define X86EMUL_RETRY_INSTR     3 /* retry the instruction for some reason */
 #define X86EMUL_CMPXCHG_FAILED  4 /* cmpxchg did not see expected value */
 #define X86EMUL_IO_NEEDED       5 /* IO is needed to complete emulation */
+#define X86EMUL_INTERCEPTED     6 /* Intercepted by nested VMCB/VMCS */
 
 struct x86_emulate_ops {
         /*
@@ -63,8 +92,10 @@ struct x86_emulate_ops {
          *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
          *  @bytes: [IN ] Number of bytes to read from memory.
          */
-        int (*read_std)(unsigned long addr, void *val,
-                        unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+        int (*read_std)(struct x86_emulate_ctxt *ctxt,
+                        unsigned long addr, void *val,
+                        unsigned int bytes,
+                        struct x86_exception *fault);
 
         /*
          * write_std: Write bytes of standard (non-emulated/special) memory.
@@ -73,8 +104,9 @@ struct x86_emulate_ops {
          *  @val:   [OUT] Value write to memory, zero-extended to 'u_long'.
          *  @bytes: [IN ] Number of bytes to write to memory.
          */
-        int (*write_std)(unsigned long addr, void *val,
-                         unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+        int (*write_std)(struct x86_emulate_ctxt *ctxt,
+                         unsigned long addr, void *val, unsigned int bytes,
+                         struct x86_exception *fault);
         /*
          * fetch: Read bytes of standard (non-emulated/special) memory.
          *        Used for instruction fetch.
@@ -82,8 +114,9 @@ struct x86_emulate_ops {
          *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
          *  @bytes: [IN ] Number of bytes to read from memory.
          */
-        int (*fetch)(unsigned long addr, void *val,
-                        unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+        int (*fetch)(struct x86_emulate_ctxt *ctxt,
+                     unsigned long addr, void *val, unsigned int bytes,
+                     struct x86_exception *fault);
 
         /*
          * read_emulated: Read bytes from emulated/special memory area.
@@ -91,11 +124,9 @@ struct x86_emulate_ops {
          *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
          *  @bytes: [IN ] Number of bytes to read from memory.
          */
-        int (*read_emulated)(unsigned long addr,
-                             void *val,
-                             unsigned int bytes,
-                             unsigned int *error,
-                             struct kvm_vcpu *vcpu);
+        int (*read_emulated)(struct x86_emulate_ctxt *ctxt,
+                             unsigned long addr, void *val, unsigned int bytes,
+                             struct x86_exception *fault);
 
         /*
          * write_emulated: Write bytes to emulated/special memory area.
@@ -104,11 +135,10 @@ struct x86_emulate_ops {
          *                required).
          *  @bytes: [IN ] Number of bytes to write to memory.
          */
-        int (*write_emulated)(unsigned long addr,
-                              const void *val,
+        int (*write_emulated)(struct x86_emulate_ctxt *ctxt,
+                              unsigned long addr, const void *val,
                               unsigned int bytes,
-                              unsigned int *error,
-                              struct kvm_vcpu *vcpu);
+                              struct x86_exception *fault);
 
         /*
          * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an
@@ -118,49 +148,72 @@ struct x86_emulate_ops {
          *  @new:   [IN ] Value to write to @addr.
          *  @bytes: [IN ] Number of bytes to access using CMPXCHG.
          */
-        int (*cmpxchg_emulated)(unsigned long addr,
+        int (*cmpxchg_emulated)(struct x86_emulate_ctxt *ctxt,
+                                unsigned long addr,
                                 const void *old,
                                 const void *new,
                                 unsigned int bytes,
-                                unsigned int *error,
-                                struct kvm_vcpu *vcpu);
-
-        int (*pio_in_emulated)(int size, unsigned short port, void *val,
-                               unsigned int count, struct kvm_vcpu *vcpu);
-
-        int (*pio_out_emulated)(int size, unsigned short port, const void *val,
-                                unsigned int count, struct kvm_vcpu *vcpu);
-
-        bool (*get_cached_descriptor)(struct desc_struct *desc,
-                                      int seg, struct kvm_vcpu *vcpu);
-        void (*set_cached_descriptor)(struct desc_struct *desc,
-                                      int seg, struct kvm_vcpu *vcpu);
-        u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu);
-        void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu);
-        unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu);
-        void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
-        ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
-        int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
-        int (*cpl)(struct kvm_vcpu *vcpu);
-        int (*get_dr)(int dr, unsigned long *dest, struct kvm_vcpu *vcpu);
-        int (*set_dr)(int dr, unsigned long value, struct kvm_vcpu *vcpu);
-        int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
-        int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+                                struct x86_exception *fault);
+        void (*invlpg)(struct x86_emulate_ctxt *ctxt, ulong addr);
+
+        int (*pio_in_emulated)(struct x86_emulate_ctxt *ctxt,
+                               int size, unsigned short port, void *val,
+                               unsigned int count);
+
+        int (*pio_out_emulated)(struct x86_emulate_ctxt *ctxt,
+                                int size, unsigned short port, const void *val,
+                                unsigned int count);
+
+        bool (*get_segment)(struct x86_emulate_ctxt *ctxt, u16 *selector,
+                            struct desc_struct *desc, u32 *base3, int seg);
+        void (*set_segment)(struct x86_emulate_ctxt *ctxt, u16 selector,
+                            struct desc_struct *desc, u32 base3, int seg);
+        unsigned long (*get_cached_segment_base)(struct x86_emulate_ctxt *ctxt,
+                                                 int seg);
+        void (*get_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+        void (*get_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+        void (*set_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+        void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+        ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
+        int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+        int (*cpl)(struct x86_emulate_ctxt *ctxt);
+        int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
+        int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
+        int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
+        int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
+        void (*halt)(struct x86_emulate_ctxt *ctxt);
+        void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
+        int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
+        void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
+        void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
+        int (*intercept)(struct x86_emulate_ctxt *ctxt,
+                         struct x86_instruction_info *info,
+                         enum x86_intercept_stage stage);
 };
 
+typedef u32 __attribute__((vector_size(16))) sse128_t;
+
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
-        enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
+        enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type;
         unsigned int bytes;
         union {
                 unsigned long orig_val;
                 u64 orig_val64;
         };
-        unsigned long *ptr;
+        union {
+                unsigned long *reg;
+                struct segmented_address {
+                        ulong ea;
+                        unsigned seg;
+                } mem;
+                unsigned xmm;
+        } addr;
         union {
                 unsigned long val;
                 u64 val64;
                 char valptr[sizeof(unsigned long) + 2];
+                sse128_t vec_val;
         };
 };
 
@@ -179,6 +232,7 @@ struct read_cache {
 struct decode_cache {
         u8 twobyte;
         u8 b;
+        u8 intercept;
         u8 lock_prefix;
         u8 rep_prefix;
         u8 op_bytes;
@@ -190,6 +244,8 @@ struct decode_cache {
         bool has_seg_override;
         u8 seg_override;
         unsigned int d;
+        int (*execute)(struct x86_emulate_ctxt *ctxt);
+        int (*check_perm)(struct x86_emulate_ctxt *ctxt);
         unsigned long regs[NR_VCPU_REGS];
         unsigned long eip;
         /* modrm */
@@ -197,43 +253,39 @@ struct decode_cache {
         u8 modrm_mod;
         u8 modrm_reg;
         u8 modrm_rm;
-        u8 use_modrm_ea;
+        u8 modrm_seg;
         bool rip_relative;
-        unsigned long modrm_ea;
-        void *modrm_ptr;
-        unsigned long modrm_val;
         struct fetch_cache fetch;
         struct read_cache io_read;
         struct read_cache mem_read;
 };
 
 struct x86_emulate_ctxt {
-        /* Register state before/after emulation. */
-        struct kvm_vcpu *vcpu;
+        struct x86_emulate_ops *ops;
 
+        /* Register state before/after emulation. */
         unsigned long eflags;
         unsigned long eip; /* eip before instruction emulation */
         /* Emulated execution mode, represented by an X86EMUL_MODE value. */
         int mode;
-        u32 cs_base;
 
         /* interruptibility state, as a result of execution of STI or MOV SS */
         int interruptibility;
 
-        bool restart; /* restart string instruction after writeback */
+        bool guest_mode; /* guest running a nested guest */
+        bool perm_ok; /* do not check permissions if true */
+        bool only_vendor_specific_insn;
 
-        int exception; /* exception that happens during emulation or -1 */
-        u32 error_code; /* error code for exception */
-        bool error_code_valid;
-        unsigned long cr2; /* faulted address in case of #PF */
+        bool have_exception;
+        struct x86_exception exception;
 
         /* decode cache */
         struct decode_cache decode;
 };
 
 /* Repeat String Operation Prefix */
-#define REPE_PREFIX     1
-#define REPNE_PREFIX    2
+#define REPE_PREFIX     0xf3
+#define REPNE_PREFIX    0xf2
 
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0 /* Real mode.             */
@@ -242,6 +294,69 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT32   4 /* 32-bit protected mode. */
 #define X86EMUL_MODE_PROT64   8 /* 64-bit (long) mode.    */
 
+/* any protected mode   */
+#define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
+                               X86EMUL_MODE_PROT64)
+
+enum x86_intercept_stage {
+        X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
+        X86_ICPT_PRE_EXCEPT,
+        X86_ICPT_POST_EXCEPT,
+        X86_ICPT_POST_MEMACCESS,
+};
+
+enum x86_intercept {
+        x86_intercept_none,
+        x86_intercept_cr_read,
+        x86_intercept_cr_write,
+        x86_intercept_clts,
+        x86_intercept_lmsw,
+        x86_intercept_smsw,
+        x86_intercept_dr_read,
+        x86_intercept_dr_write,
+        x86_intercept_lidt,
+        x86_intercept_sidt,
+        x86_intercept_lgdt,
+        x86_intercept_sgdt,
+        x86_intercept_lldt,
+        x86_intercept_sldt,
+        x86_intercept_ltr,
+        x86_intercept_str,
+        x86_intercept_rdtsc,
+        x86_intercept_rdpmc,
+        x86_intercept_pushf,
+        x86_intercept_popf,
+        x86_intercept_cpuid,
+        x86_intercept_rsm,
+        x86_intercept_iret,
+        x86_intercept_intn,
+        x86_intercept_invd,
+        x86_intercept_pause,
+        x86_intercept_hlt,
+        x86_intercept_invlpg,
+        x86_intercept_invlpga,
+        x86_intercept_vmrun,
+        x86_intercept_vmload,
+        x86_intercept_vmsave,
+        x86_intercept_vmmcall,
+        x86_intercept_stgi,
+        x86_intercept_clgi,
+        x86_intercept_skinit,
+        x86_intercept_rdtscp,
+        x86_intercept_icebp,
+        x86_intercept_wbinvd,
+        x86_intercept_monitor,
+        x86_intercept_mwait,
+        x86_intercept_rdmsr,
+        x86_intercept_wrmsr,
+        x86_intercept_in,
+        x86_intercept_ins,
+        x86_intercept_out,
+        x86_intercept_outs,
+
+        nr_x86_intercepts
+};
+
 /* Host execution mode. */
 #if defined(CONFIG_X86_32)
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
@@ -249,13 +364,15 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
-                    struct x86_emulate_ops *ops);
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
-                     struct x86_emulate_ops *ops);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+#define EMULATION_FAILED -1
+#define EMULATION_OK 0
+#define EMULATION_RESTART 1
+#define EMULATION_INTERCEPTED 2
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-                         struct x86_emulate_ops *ops,
                          u16 tss_selector, int reason,
                          bool has_error_code, u32 error_code);
-
+int emulate_int_real(struct x86_emulate_ctxt *ctxt,
+                     struct x86_emulate_ops *ops, int irq);
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c52e2eb40a1e..d2ac8e2ee897 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -30,14 +30,30 @@
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_MMIO_SIZE 16
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
+#define CR0_RESERVED_BITS                                               \
+        (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
+                          | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
+                          | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
+
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |    \
                                   0xFFFFFF0000000000ULL)
+#define CR4_RESERVED_BITS                                               \
+        (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
+                          | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
+                          | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR  \
+                          | X86_CR4_OSXSAVE \
+                          | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+
+#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
+
+
 
 #define INVALID_PAGE (~(hpa_t)0)
 #define VALID_PAGE(x) ((x) != INVALID_PAGE)
@@ -79,15 +95,18 @@
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 
-extern spinlock_t kvm_lock;
+#define ASYNC_PF_PER_VCPU 64
+
+extern raw_spinlock_t kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_vcpu;
 struct kvm;
+struct kvm_async_pf;
 
 enum kvm_reg {
         VCPU_REGS_RAX = 0,
@@ -114,6 +133,10 @@ enum kvm_reg {
 
 enum kvm_reg_ex {
         VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+        VCPU_EXREG_CR3,
+        VCPU_EXREG_RFLAGS,
+        VCPU_EXREG_CPL,
+        VCPU_EXREG_SEGMENTS,
 };
 
 enum {
@@ -236,26 +259,39 @@ struct kvm_pio_request {
  */
 struct kvm_mmu {
         void (*new_cr3)(struct kvm_vcpu *vcpu);
-        int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
+        void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
+        unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
+        int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+                          bool prefault);
+        void (*inject_page_fault)(struct kvm_vcpu *vcpu,
+                                  struct x86_exception *fault);
         void (*free)(struct kvm_vcpu *vcpu);
         gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-                            u32 *error);
+                            struct x86_exception *exception);
+        gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
         void (*prefetch_page)(struct kvm_vcpu *vcpu,
                               struct kvm_mmu_page *page);
         int (*sync_page)(struct kvm_vcpu *vcpu,
-                         struct kvm_mmu_page *sp, bool clear_unsync);
+                         struct kvm_mmu_page *sp);
         void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
+        void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+                           u64 *spte, const void *pte);
         hpa_t root_hpa;
         int root_level;
         int shadow_root_level;
         union kvm_mmu_page_role base_role;
+        bool direct_map;
 
         u64 *pae_root;
+        u64 *lm_root;
         u64 rsvd_bits_mask[2][4];
+
+        bool nx;
+
+        u64 pdptrs[4]; /* pae */
 };
 
 struct kvm_vcpu_arch {
-        u64 host_tsc;
         /*
          * rip and regs accesses must go through
          * kvm_{register,rip}_{read,write} functions.
@@ -272,7 +308,6 @@ struct kvm_vcpu_arch {
         unsigned long cr4_guest_owned_bits;
         unsigned long cr8;
         u32 hflags;
-        u64 pdptrs[4]; /* pae */
         u64 efer;
         u64 apic_base;
         struct kvm_lapic *apic;    /* kernel irqchip context */
@@ -282,7 +317,31 @@ struct kvm_vcpu_arch {
         u64 ia32_misc_enable_msr;
         bool tpr_access_reporting;
 
+        /*
+         * Paging state of the vcpu
+         *
+         * If the vcpu runs in guest mode with two level paging this still saves
+         * the paging mode of the l1 guest. This context is always used to
+         * handle faults.
+         */
         struct kvm_mmu mmu;
+
+        /*
+         * Paging state of an L2 guest (used for nested npt)
+         *
+         * This context will save all necessary information to walk page tables
+         * of the an L2 guest. This context is only initialized for page table
+         * walking and not for faulting since we never handle l2 page faults on
+         * the host.
+         */
+        struct kvm_mmu nested_mmu;
+
+        /*
+         * Pointer to the mmu context currently used for
+         * gva_to_gpa translations.
+         */
+        struct kvm_mmu *walk_mmu;
+
         /* only needed in kvm_pv_mmu_op() path, but it's hot so
          * put it here to avoid allocation */
         struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -297,16 +356,9 @@ struct kvm_vcpu_arch {
         u64  *last_pte_updated;
         gfn_t last_pte_gfn;
 
-        struct {
-                gfn_t gfn;      /* presumed gfn during guest pte update */
-                pfn_t pfn;      /* pfn corresponding to that gfn */
-                unsigned long mmu_seq;
-        } update_pte;
-
         struct fpu guest_fpu;
         u64 xcr0;
 
-        gva_t mmio_fault_cr2;
         struct kvm_pio_request pio;
         void *pio_data;
 
@@ -333,12 +385,22 @@ struct kvm_vcpu_arch {
         /* emulate context */
 
         struct x86_emulate_ctxt emulate_ctxt;
+        bool emulate_regs_need_sync_to_vcpu;
+        bool emulate_regs_need_sync_from_vcpu;
 
         gpa_t time;
         struct pvclock_vcpu_time_info hv_clock;
-        unsigned int hv_clock_tsc_khz;
+        unsigned int hw_tsc_khz;
         unsigned int time_offset;
         struct page *time_page;
+        u64 last_guest_tsc;
+        u64 last_kernel_ns;
+        u64 last_tsc_nsec;
+        u64 last_tsc_write;
+        u32 virtual_tsc_khz;
+        bool tsc_catchup;
+        u32  tsc_catchup_mult;
+        s8   tsc_catchup_shift;
 
         bool nmi_pending;
         bool nmi_injected;
@@ -364,12 +426,21 @@ struct kvm_vcpu_arch {
         u64 hv_vapic;
 
         cpumask_var_t wbinvd_dirty_mask;
+
+        struct {
+                bool halted;
+                gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+                struct gfn_to_hva_cache data;
+                u64 msr_val;
+                u32 id;
+                bool send_user_only;
+        } apf;
 };
 
 struct kvm_arch {
-        unsigned int n_free_mmu_pages;
+        unsigned int n_used_mmu_pages;
         unsigned int n_requested_mmu_pages;
-        unsigned int n_alloc_mmu_pages;
+        unsigned int n_max_mmu_pages;
         atomic_t invlpg_counter;
         struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
         /*
@@ -394,14 +465,21 @@ struct kvm_arch {
         gpa_t ept_identity_map_addr;
 
         unsigned long irq_sources_bitmap;
-        u64 vm_init_tsc;
         s64 kvmclock_offset;
+        raw_spinlock_t tsc_write_lock;
+        u64 last_tsc_nsec;
+        u64 last_tsc_offset;
+        u64 last_tsc_write;
 
         struct kvm_xen_hvm_config xen_hvm_config;
 
         /* fields used by HYPER-V emulation */
         u64 hv_guest_os_id;
         u64 hv_hypercall;
+
+        #ifdef CONFIG_KVM_MMU_AUDIT
+        int audit_point;
+        #endif
 };
 
 struct kvm_vm_stat {
@@ -443,6 +521,8 @@ struct kvm_vcpu_stat {
         u32 nmi_injections;
 };
 
+struct x86_instruction_info;
+
 struct kvm_x86_ops {
         int (*cpu_has_kvm_support)(void);          /* __init */
         int (*disabled_by_bios)(void);             /* __init */
@@ -475,6 +555,7 @@ struct kvm_x86_ops {
                             struct kvm_segment *var, int seg);
         void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
         void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
+        void (*decache_cr3)(struct kvm_vcpu *vcpu);
         void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
         void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
         void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -505,6 +586,7 @@ struct kvm_x86_ops {
         void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
                                 bool has_error_code, u32 error_code,
                                 bool reinject);
+        void (*cancel_injection)(struct kvm_vcpu *vcpu);
         int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
         int (*nmi_allowed)(struct kvm_vcpu *vcpu);
         bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
@@ -517,14 +599,35 @@ struct kvm_x86_ops {
         u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
         int (*get_lpage_level)(void);
         bool (*rdtscp_supported)(void);
+        void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+
+        void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
         void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);
 
         bool (*has_wbinvd_exit)(void);
 
+        void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
+        void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+
+        u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
+
+        void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
+
+        int (*check_intercept)(struct kvm_vcpu *vcpu,
+                               struct x86_instruction_info *info,
+                               enum x86_intercept_stage stage);
+
         const struct trace_print_flags *exit_reasons_str;
 };
 
+struct kvm_arch_async_pf {
+        u32 token;
+        gfn_t gfn;
+        unsigned long cr3;
+        bool direct_map;
+};
+
 extern struct kvm_x86_ops *kvm_x86_ops;
 
 int kvm_mmu_module_init(void);
@@ -534,7 +637,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
 int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
-void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
                 u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
@@ -544,7 +646,7 @@ void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
                           const void *val, int bytes);
@@ -554,6 +656,13 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
 
+/* control of guest tsc rate supported? */
+extern bool kvm_has_tsc_control;
+/* minimum supported tsc_khz for guests */
+extern u32  kvm_min_guest_tsc_khz;
+/* maximum supported tsc_khz for guests */
+extern u32  kvm_max_guest_tsc_khz;
+
 enum emulation_result {
         EMULATE_DONE,       /* no further processing */
         EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
@@ -563,10 +672,14 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE          (1 << 0)
 #define EMULTYPE_TRAP_UD            (1 << 1)
 #define EMULTYPE_SKIP               (1 << 2)
-int emulate_instruction(struct kvm_vcpu *vcpu,
-                        unsigned long cr2, u16 error_code, int emulation_type);
-void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+                            int emulation_type, void *insn, int insn_len);
+
+static inline int emulate_instruction(struct kvm_vcpu *vcpu,
+                        int emulation_type)
+{
+        return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
 
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
@@ -577,8 +690,6 @@ struct x86_emulate_ctxt;
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
-int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
-int emulate_clts(struct kvm_vcpu *vcpu);
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -590,7 +701,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
 int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
@@ -608,8 +719,11 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
-                           u32 error_code);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
+int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+                            gfn_t gfn, void *data, int offset, int len,
+                            u32 access);
+void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);
@@ -627,16 +741,19 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
-gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
+                              struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
+                               struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
+                               struct x86_exception *exception);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
+                                struct x86_exception *exception);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
-
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+                       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 
 void kvm_enable_tdp(void);
@@ -703,20 +820,25 @@ enum {
 #define HF_VINTR_MASK           (1 << 2)
 #define HF_NMI_MASK             (1 << 3)
 #define HF_IRET_MASK            (1 << 4)
+#define HF_GUEST_MASK           (1 << 5) /* VCPU is in guest-mode */
 
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
  * Trap the fault and ignore the instruction if that happens.
  */
-asmlinkage void kvm_handle_fault_on_reboot(void);
+asmlinkage void kvm_spurious_fault(void);
+extern bool kvm_rebooting;
 
 #define __kvm_handle_fault_on_reboot(insn) \
         "666: " insn "\n\t" \
+        "668: \n\t"                           \
         ".pushsection .fixup, \"ax\" \n" \
         "667: \n\t" \
+        "cmpb $0, kvm_rebooting \n\t"         \
+        "jne 668b \n\t"                       \
         __ASM_SIZE(push) " $666b \n\t"        \
-        "jmp kvm_handle_fault_on_reboot \n\t" \
+        "call kvm_spurious_fault \n\t"        \
         ".popsection \n\t" \
         ".pushsection __ex_table, \"a\" \n\t" \
         _ASM_PTR " 666b, 667b \n\t" \
@@ -725,6 +847,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
@@ -736,4 +859,15 @@ void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+                                     struct kvm_async_pf *work);
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+                                 struct kvm_async_pf *work);
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+                               struct kvm_async_pf *work);
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+
+void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 05eba5e9a8e8..a427bf77a93d 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -20,6 +20,7 @@
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
+#define KVM_FEATURE_ASYNC_PF            4
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -32,9 +33,13 @@
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+#define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 
 #define KVM_MAX_MMU_OP_BATCH           32
 
+#define KVM_ASYNC_PF_ENABLED                    (1 << 0)
+#define KVM_ASYNC_PF_SEND_ALWAYS                (1 << 1)
+
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
 #define KVM_MMU_OP_FLUSH_TLB            2
@@ -61,10 +66,20 @@ struct kvm_mmu_op_release_pt {
         __u64 pt_phys;
 };
 
+#define KVM_PV_REASON_PAGE_NOT_PRESENT 1
+#define KVM_PV_REASON_PAGE_READY 2
+
+struct kvm_vcpu_pv_apf_data {
+        __u32 reason;
+        __u8 pad[60];
+        __u32 enabled;
+};
+
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
 extern void kvmclock_init(void);
+extern int kvm_register_clock(char *txt);
 
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
@@ -158,6 +173,21 @@ static inline unsigned int kvm_arch_para_features(void)
         return cpuid_eax(KVM_CPUID_FEATURES);
 }
 
+#ifdef CONFIG_KVM_GUEST
+void __init kvm_guest_init(void);
+void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wake(u32 token);
+u32 kvm_read_and_reset_pf_reason(void);
+#else
+#define kvm_guest_init() do { } while (0)
+#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wake(T) do {} while(0)
+static inline u32 kvm_read_and_reset_pf_reason(void)
+{
+        return 0;
+}
 #endif
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 12d55e773eb6..48142971b25d 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,11 +8,6 @@
 
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
-/*
- * For 32-bit UML - mark functions implemented in assembly that use
- * regparm input parameters:
- */
-#define asmregparm __attribute__((regparm(3)))
 
 /*
  * Make sure the compiler doesn't do anything stupid with the
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..021979a6e23f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -142,8 +142,6 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
-extern void (*x86_mce_decode_callback)(struct mce *m);
-
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
@@ -223,6 +221,9 @@ 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/memblock.h b/arch/x86/include/asm/memblock.h
new file mode 100644
index 000000000000..0cd3800f33b9
--- /dev/null
+++ b/arch/x86/include/asm/memblock.h
@@ -0,0 +1,23 @@
+#ifndef _X86_MEMBLOCK_H
+#define _X86_MEMBLOCK_H
+
+#define ARCH_DISCARD_MEMBLOCK
+
+u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
+
+void memblock_x86_reserve_range(u64 start, u64 end, char *name);
+void memblock_x86_free_range(u64 start, u64 end);
+struct range;
+int __get_free_all_memory_range(struct range **range, int nodeid,
+                         unsigned long start_pfn, unsigned long end_pfn);
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
+void memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+                                         unsigned long last_pfn);
+u64 memblock_x86_hole_size(u64 start, u64 end);
+u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
+u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
+u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
+
+#endif
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/mmu.h b/arch/x86/include/asm/mmu.h
index 80a1dee5bea5..5f55e6962769 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -11,6 +11,12 @@
 typedef struct {
         void *ldt;
         int size;
+
+#ifdef CONFIG_X86_64
+        /* True if mm supports a task running in 32 bit compatibility mode. */
+        unsigned short ia32_compat;
+#endif
+
         struct mutex lock;
         void *vdso;
 } mm_context_t;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 4a2d4e0c18d9..8b5393ec1080 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -36,8 +36,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
         unsigned cpu = smp_processor_id();
 
         if (likely(prev != next)) {
-                /* stop flush ipis for the previous mm */
-                cpumask_clear_cpu(cpu, mm_cpumask(prev));
 #ifdef CONFIG_SMP
                 percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
                 percpu_write(cpu_tlbstate.active_mm, next);
@@ -47,6 +45,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                 /* Re-load page tables */
                 load_cr3(next->pgd);
 
+                /* stop flush ipis for the previous mm */
+                cpumask_clear_cpu(cpu, mm_cpumask(prev));
+
                 /*
                  * load the LDT, if the LDT is different:
                  */
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 91df7c51806c..ffa037f28d39 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -13,31 +13,11 @@ extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)  (node_data[nid])
 
 #include <asm/numaq.h>
-/* summit or generic arch */
-#include <asm/srat.h>
-
-extern int get_memcfg_numa_flat(void);
-/*
- * This allows any one NUMA architecture to be compiled
- * for, and still fall back to the flat function if it
- * fails.
- */
-static inline void get_memcfg_numa(void)
-{
-
-        if (get_memcfg_numaq())
-                return;
-        if (get_memcfg_from_srat())
-                return;
-        get_memcfg_numa_flat();
-}
 
 extern void resume_map_numa_kva(pgd_t *pgd);
 
 #else /* !CONFIG_NUMA */
 
-#define get_memcfg_numa get_memcfg_numa_flat
-
 static inline void resume_map_numa_kva(pgd_t *pgd) {}
 
 #endif /* CONFIG_NUMA */
@@ -68,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)                                               \
-({                                                                      \
-        pg_data_t *__pgdat = NODE_DATA(nid);                            \
-        __pgdat->node_start_pfn + __pgdat->node_spanned_pages;          \
-})
-
 static inline int pfn_valid(int pfn)
 {
         int nid = pfn_to_nid(pfn);
@@ -88,6 +57,8 @@ static inline int pfn_valid(int pfn)
         return 0;
 }
 
+#define early_pfn_valid(pfn)    pfn_valid((pfn))
+
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index 288b96f815a6..129d9aa3ceb3 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -4,40 +4,14 @@
 #ifndef _ASM_X86_MMZONE_64_H
 #define _ASM_X86_MMZONE_64_H
 
-
 #ifdef CONFIG_NUMA
 
 #include <linux/mmdebug.h>
-
 #include <asm/smp.h>
 
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
-        int shift;
-        unsigned int mapsize;
-        s16 *map;
-        s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
 extern struct pglist_data *node_data[];
 
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
-        unsigned nid;
-        VIRTUAL_BUG_ON(!memnodemap);
-        nid = memnodemap[addr >> memnode_shift];
-        VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
-        return nid;
-}
-
 #define NODE_DATA(nid)          (node_data[nid])
 
-#define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +       \
-                                 NODE_DATA(nid)->node_spanned_pages)
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 3e2ce58a31a3..9eae7752ae9b 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -35,7 +35,7 @@
 #define MODULE_PROC_FAMILY "K7 "
 #elif defined CONFIG_MK8
 #define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_X86_ELAN
+#elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
 #define MODULE_PROC_FAMILY "CRUSOE "
@@ -60,12 +60,7 @@
 #endif
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
 #endif
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index c82868e9f905..9c7d95f6174b 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
@@ -24,7 +25,6 @@ extern int pic_mode;
 #define MAX_IRQ_SOURCES         256
 
 extern unsigned int def_to_bigsmp;
-extern u8 apicid_2_node[];
 
 #ifdef CONFIG_X86_NUMAQ
 extern int mp_bus_id_to_node[MAX_MP_BUSSES];
@@ -32,8 +32,6 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];
 extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 #endif
 
-#define MAX_APICID              256
-
 #else /* CONFIG_X86_64: */
 
 #define MAX_MP_BUSSES           256
@@ -107,7 +105,7 @@ 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 +120,31 @@ 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 +157,6 @@ 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 16350740edf6..719f00b28ff5 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -10,8 +10,13 @@
  */
 #ifndef _ASM_X86_MRST_H
 #define _ASM_X86_MRST_H
+
+#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
@@ -26,7 +31,7 @@ enum mrst_cpu_type {
 };
 
 extern enum mrst_cpu_type __mrst_cpu_chip;
-static enum mrst_cpu_type mrst_identify_cpu(void)
+static inline enum mrst_cpu_type mrst_identify_cpu(void)
 {
         return __mrst_cpu_chip;
 }
@@ -42,4 +47,19 @@ extern enum mrst_timer_options mrst_timer_options;
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX    8
 
+extern struct console early_mrst_console;
+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 986f7790fdb2..485b4f1f079b 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -36,8 +36,14 @@
 #define MSR_IA32_PERFCTR1               0x000000c2
 #define MSR_FSB_FREQ                    0x000000cd
 
+#define MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
+#define NHM_C3_AUTO_DEMOTE              (1UL << 25)
+#define NHM_C1_AUTO_DEMOTE              (1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE          (1UL << 25)
+
 #define MSR_MTRRcap                     0x000000fe
 #define MSR_IA32_BBL_CR_CTL             0x00000119
+#define MSR_IA32_BBL_CR_CTL3            0x0000011e
 
 #define MSR_IA32_SYSENTER_CS            0x00000174
 #define MSR_IA32_SYSENTER_ESP           0x00000175
@@ -47,6 +53,9 @@
 #define MSR_IA32_MCG_STATUS             0x0000017a
 #define MSR_IA32_MCG_CTL                0x0000017b
 
+#define MSR_OFFCORE_RSP_0               0x000001a6
+#define MSR_OFFCORE_RSP_1               0x000001a7
+
 #define MSR_IA32_PEBS_ENABLE            0x000003f1
 #define MSR_IA32_DS_AREA                0x00000600
 #define MSR_IA32_PERF_CAPABILITIES      0x00000345
@@ -87,11 +96,15 @@
 #define MSR_IA32_MC0_ADDR               0x00000402
 #define MSR_IA32_MC0_MISC               0x00000403
 
+#define MSR_AMD64_MC0_MASK              0xc0010044
+
 #define MSR_IA32_MCx_CTL(x)             (MSR_IA32_MC0_CTL + 4*(x))
 #define MSR_IA32_MCx_STATUS(x)          (MSR_IA32_MC0_STATUS + 4*(x))
 #define MSR_IA32_MCx_ADDR(x)            (MSR_IA32_MC0_ADDR + 4*(x))
 #define MSR_IA32_MCx_MISC(x)            (MSR_IA32_MC0_MISC + 4*(x))
 
+#define MSR_AMD64_MCx_MASK(x)           (MSR_AMD64_MC0_MASK + (x))
+
 /* These are consecutive and not in the normal 4er MCE bank block */
 #define MSR_IA32_MC0_CTL2               0x00000280
 #define MSR_IA32_MCx_CTL2(x)            (MSR_IA32_MC0_CTL2 + (x))
@@ -105,6 +118,7 @@
    complete list. */
 
 #define MSR_AMD64_PATCH_LEVEL           0x0000008b
+#define MSR_AMD64_TSC_RATIO             0xc0000104
 #define MSR_AMD64_NB_CFG                0xc001001f
 #define MSR_AMD64_PATCH_LOADER          0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH        0xc0010140
@@ -121,13 +135,18 @@
 #define MSR_AMD64_IBSDCLINAD            0xc0011038
 #define MSR_AMD64_IBSDCPHYSAD           0xc0011039
 #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)
 #define FAM10H_MMIO_CONF_BUSRANGE_MASK  0xf
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK      0xfffffff
+#define FAM10H_MMIO_CONF_BASE_MASK      0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT     20
 #define MSR_FAM10H_NODE_ID              0xc001100c
 
@@ -198,6 +217,7 @@
 #define MSR_IA32_TSC                    0x00000010
 #define MSR_IA32_PLATFORM_ID            0x00000017
 #define MSR_IA32_EBL_CR_POWERON         0x0000002a
+#define MSR_EBC_FREQUENCY_ID            0x0000002c
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
 #define FEATURE_CONTROL_LOCKED                          (1<<0)
@@ -251,6 +271,18 @@
 #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/mwait.h b/arch/x86/include/asm/mwait.h
new file mode 100644
index 000000000000..bcdff997668c
--- /dev/null
+++ b/arch/x86/include/asm/mwait.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_X86_MWAIT_H
+#define _ASM_X86_MWAIT_H
+
+#define MWAIT_SUBSTATE_MASK             0xf
+#define MWAIT_CSTATE_MASK               0xf
+#define MWAIT_SUBSTATE_SIZE             4
+#define MWAIT_MAX_NUM_CSTATES           8
+
+#define CPUID_MWAIT_LEAF                5
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1
+#define CPUID5_ECX_INTERRUPT_BREAK      0x2
+
+#define MWAIT_ECX_INTERRUPT_BREAK       0x1
+
+#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 932f0f86b4b7..4886a68f267e 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -5,41 +5,14 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 
-#ifdef ARCH_HAS_NMI_WATCHDOG
+#ifdef CONFIG_X86_LOCAL_APIC
 
-/**
- * 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);
-
-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 +20,28 @@ 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 separate
+ * the priorities.  This can go a lot 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/nops.h b/arch/x86/include/asm/nops.h
index 6d8723a766cc..405b4032a60b 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -1,7 +1,13 @@
 #ifndef _ASM_X86_NOPS_H
 #define _ASM_X86_NOPS_H
 
-/* Define nops for use with alternative() */
+/*
+ * Define nops for use with alternative() and for tracing.
+ *
+ * *_NOP5_ATOMIC must be a single instruction.
+ */
+
+#define NOP_DS_PREFIX 0x3e
 
 /* generic versions from gas
    1: nop
@@ -13,14 +19,15 @@
    6: leal 0x00000000(%esi),%esi
    7: leal 0x00000000(,%esi,1),%esi
 */
-#define GENERIC_NOP1 ".byte 0x90\n"
-#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
-#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
-#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
-#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
-#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
+#define GENERIC_NOP1 0x90
+#define GENERIC_NOP2 0x89,0xf6
+#define GENERIC_NOP3 0x8d,0x76,0x00
+#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
+#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
+#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
+#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
+#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
 
 /* Opteron 64bit nops
    1: nop
@@ -29,16 +36,17 @@
    4: osp osp osp nop
 */
 #define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2 ".byte 0x66,0x90\n"
-#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
-#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
-#define K8_NOP5 K8_NOP3 K8_NOP2
-#define K8_NOP6 K8_NOP3 K8_NOP3
-#define K8_NOP7 K8_NOP4 K8_NOP3
-#define K8_NOP8 K8_NOP4 K8_NOP4
+#define K8_NOP2 0x66,K8_NOP1
+#define K8_NOP3 0x66,K8_NOP2
+#define K8_NOP4 0x66,K8_NOP3
+#define K8_NOP5 K8_NOP3,K8_NOP2
+#define K8_NOP6 K8_NOP3,K8_NOP3
+#define K8_NOP7 K8_NOP4,K8_NOP3
+#define K8_NOP8 K8_NOP4,K8_NOP4
+#define K8_NOP5_ATOMIC 0x66,K8_NOP4
 
 /* K7 nops
-   uses eax dependencies (arbitary choice)
+   uses eax dependencies (arbitrary choice)
    1: nop
    2: movl %eax,%eax
    3: leal (,%eax,1),%eax
@@ -47,13 +55,14 @@
    7: leal 0x00000000(,%eax,1),%eax
 */
 #define K7_NOP1 GENERIC_NOP1
-#define K7_NOP2 ".byte 0x8b,0xc0\n"
-#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
-#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
-#define K7_NOP5 K7_NOP4 ASM_NOP1
-#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
-#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n"
-#define K7_NOP8 K7_NOP7 ASM_NOP1
+#define K7_NOP2 0x8b,0xc0
+#define K7_NOP3 0x8d,0x04,0x20
+#define K7_NOP4 0x8d,0x44,0x20,0x00
+#define K7_NOP5 K7_NOP4,K7_NOP1
+#define K7_NOP6 0x8d,0x80,0,0,0,0
+#define K7_NOP7 0x8D,0x04,0x05,0,0,0,0
+#define K7_NOP8 K7_NOP7,K7_NOP1
+#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
 
 /* P6 nops
    uses eax dependencies (Intel-recommended choice)
@@ -69,52 +78,65 @@
         There is kernel code that depends on this.
 */
 #define P6_NOP1 GENERIC_NOP1
-#define P6_NOP2 ".byte 0x66,0x90\n"
-#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
-#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
-#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
-#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+#define P6_NOP2 0x66,0x90
+#define P6_NOP3 0x0f,0x1f,0x00
+#define P6_NOP4 0x0f,0x1f,0x40,0
+#define P6_NOP5 0x0f,0x1f,0x44,0x00,0
+#define P6_NOP6 0x66,0x0f,0x1f,0x44,0x00,0
+#define P6_NOP7 0x0f,0x1f,0x80,0,0,0,0
+#define P6_NOP8 0x0f,0x1f,0x84,0x00,0,0,0,0
+#define P6_NOP5_ATOMIC P6_NOP5
+
+#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
 
 #if defined(CONFIG_MK7)
-#define ASM_NOP1 K7_NOP1
-#define ASM_NOP2 K7_NOP2
-#define ASM_NOP3 K7_NOP3
-#define ASM_NOP4 K7_NOP4
-#define ASM_NOP5 K7_NOP5
-#define ASM_NOP6 K7_NOP6
-#define ASM_NOP7 K7_NOP7
-#define ASM_NOP8 K7_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
 #elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 P6_NOP1
-#define ASM_NOP2 P6_NOP2
-#define ASM_NOP3 P6_NOP3
-#define ASM_NOP4 P6_NOP4
-#define ASM_NOP5 P6_NOP5
-#define ASM_NOP6 P6_NOP6
-#define ASM_NOP7 P6_NOP7
-#define ASM_NOP8 P6_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
 #elif defined(CONFIG_X86_64)
-#define ASM_NOP1 K8_NOP1
-#define ASM_NOP2 K8_NOP2
-#define ASM_NOP3 K8_NOP3
-#define ASM_NOP4 K8_NOP4
-#define ASM_NOP5 K8_NOP5
-#define ASM_NOP6 K8_NOP6
-#define ASM_NOP7 K8_NOP7
-#define ASM_NOP8 K8_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
 #else
-#define ASM_NOP1 GENERIC_NOP1
-#define ASM_NOP2 GENERIC_NOP2
-#define ASM_NOP3 GENERIC_NOP3
-#define ASM_NOP4 GENERIC_NOP4
-#define ASM_NOP5 GENERIC_NOP5
-#define ASM_NOP6 GENERIC_NOP6
-#define ASM_NOP7 GENERIC_NOP7
-#define ASM_NOP8 GENERIC_NOP8
+#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
+#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
 #endif
 
 #define ASM_NOP_MAX 8
+#define NOP_ATOMIC5 (ASM_NOP_MAX+1)     /* Entry for the 5-byte atomic NOP */
+
+#ifndef __ASSEMBLY__
+extern const unsigned char * const *ideal_nops;
+extern void arch_init_ideal_nops(void);
+#endif
 
 #endif /* _ASM_X86_NOPS_H */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 27da400d3138..bfacd2ccf651 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,5 +1,85 @@
+#ifndef _ASM_X86_NUMA_H
+#define _ASM_X86_NUMA_H
+
+#include <linux/nodemask.h>
+
+#include <asm/topology.h>
+#include <asm/apicdef.h>
+
+#ifdef CONFIG_NUMA
+
+#define NR_NODE_MEMBLKS         (MAX_NUMNODES*2)
+#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
+
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
+extern int numa_off;
+
+/*
+ * __apicid_to_node[] stores the raw mapping between physical apicid and
+ * node and is used to initialize cpu_to_node mapping.
+ *
+ * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus
+ * should be accessed by the accessors - set_apicid_to_node() and
+ * numa_cpu_node().
+ */
+extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern void __init numa_set_distance(int from, int to, int distance);
+
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+        __apicid_to_node[apicid] = node;
+}
+
+extern int __cpuinit numa_cpu_node(int cpu);
+
+#else   /* CONFIG_NUMA */
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+}
+
+static inline int numa_cpu_node(int cpu)
+{
+        return NUMA_NO_NODE;
+}
+#endif  /* CONFIG_NUMA */
+
 #ifdef CONFIG_X86_32
 # include "numa_32.h"
 #else
 # include "numa_64.h"
 #endif
+
+#ifdef CONFIG_NUMA
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __init init_cpu_to_node(void);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
+#else   /* CONFIG_NUMA */
+static inline void numa_set_node(int cpu, int node)     { }
+static inline void numa_clear_node(int cpu)             { }
+static inline void init_cpu_to_node(void)               { }
+static inline void numa_add_cpu(int cpu)                { }
+static inline void numa_remove_cpu(int cpu)             { }
+#endif  /* CONFIG_NUMA */
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+void debug_cpumask_set_cpu(int cpu, int node, bool enable);
+#endif
+
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE      ((u64)32 << 20)
+#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
+void numa_emu_cmdline(char *);
+#endif /* CONFIG_NUMA_EMU */
+
+#endif  /* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index a37229011b56..e7d6b8254742 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -1,9 +1,6 @@
 #ifndef _ASM_X86_NUMA_32_H
 #define _ASM_X86_NUMA_32_H
 
-extern int pxm_to_nid(int pxm);
-extern void numa_remove_cpu(int cpu);
-
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
 #else
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 823e070e7c26..0c05f7ae46e8 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -1,52 +1,6 @@
 #ifndef _ASM_X86_NUMA_64_H
 #define _ASM_X86_NUMA_64_H
 
-#include <linux/nodemask.h>
-#include <asm/apicdef.h>
-
-struct bootnode {
-        u64 start;
-        u64 end;
-};
-
-extern int compute_hash_shift(struct bootnode *nodes, int numblks,
-                              int *nodeids);
-
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
-
-extern void numa_init_array(void);
-extern int numa_off;
-
-extern s16 apicid_to_node[MAX_LOCAL_APIC];
-
 extern unsigned long numa_free_all_bootmem(void);
-extern void setup_node_bootmem(int nodeid, unsigned long start,
-                               unsigned long end);
-
-#ifdef CONFIG_NUMA
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
-extern void __init init_cpu_to_node(void);
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
-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_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
-#endif /* CONFIG_NUMA_EMU */
-#else
-static inline void init_cpu_to_node(void)               { }
-static inline void numa_set_node(int cpu, int node)     { }
-static inline void numa_clear_node(int cpu)             { }
-static inline void numa_add_cpu(int cpu, int node)      { }
-static inline void numa_remove_cpu(int cpu)             { }
-#endif
 
 #endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 37c516545ec8..c3b3c322fd87 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -29,7 +29,7 @@
 #ifdef CONFIG_X86_NUMAQ
 
 extern int found_numaq;
-extern int get_memcfg_numaq(void);
+extern int numaq_numa_init(void);
 extern int pci_numaq_init(void);
 
 extern void *xquad_portio;
@@ -166,11 +166,6 @@ struct sys_cfg_data {
 
 void numaq_tsc_disable(void);
 
-#else
-static inline int get_memcfg_numaq(void)
-{
-        return 0;
-}
 #endif /* CONFIG_X86_NUMAQ */
 #endif /* _ASM_X86_NUMAQ_H */
 
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index 101229b0d8ed..5ca6801b75f3 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -20,7 +20,7 @@ extern struct olpc_platform_t olpc_platform_info;
 
 /*
  * OLPC board IDs contain the major build number within the mask 0x0ff0,
- * and the minor build number withing 0x000f.  Pre-builds have a minor
+ * and the minor build number within 0x000f.  Pre-builds have a minor
  * number less than 8, and normal builds start at 8.  For example, 0x0B10
  * is a PreB1, and 0x0C18 is a C1.
  */
@@ -89,6 +89,8 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 /* EC commands */
 
 #define EC_FIRMWARE_REV         0x08
+#define EC_WLAN_ENTER_RESET     0x35
+#define EC_WLAN_LEAVE_RESET     0x25
 
 /* SCI source values */
 
@@ -105,10 +107,14 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 /* GPIO assignments */
 
 #define OLPC_GPIO_MIC_AC        1
-#define OLPC_GPIO_DCON_IRQ      geode_gpio(7)
+#define OLPC_GPIO_DCON_STAT0    5
+#define OLPC_GPIO_DCON_STAT1    6
+#define OLPC_GPIO_DCON_IRQ      7
 #define OLPC_GPIO_THRM_ALRM     geode_gpio(10)
-#define OLPC_GPIO_SMB_CLK       geode_gpio(14)
-#define OLPC_GPIO_SMB_DATA      geode_gpio(15)
+#define OLPC_GPIO_DCON_LOAD    11
+#define OLPC_GPIO_DCON_BLANK   12
+#define OLPC_GPIO_SMB_CLK      14
+#define OLPC_GPIO_SMB_DATA     15
 #define OLPC_GPIO_WORKAUX       geode_gpio(24)
 #define OLPC_GPIO_LID           geode_gpio(26)
 #define OLPC_GPIO_ECSCI         geode_gpio(27)
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 08fde475cb3b..24487712e0b1 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -6,7 +6,9 @@
 
 #define OLPC_OFW_SIG 0x2057464F /* aka "OFW " */
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
+#ifdef CONFIG_OLPC
+
+extern bool olpc_ofw_is_installed(void);
 
 /* run an OFW command by calling into the firmware */
 #define olpc_ofw(name, args, res) \
@@ -21,11 +23,15 @@ extern void olpc_ofw_detect(void);
 /* install OFW's pde permanently into the kernel's pgtable */
 extern void setup_olpc_ofw_pgd(void);
 
-#else /* !CONFIG_OLPC_OPENFIRMWARE */
+/* check if OFW was detected during boot */
+extern bool olpc_ofw_present(void);
+
+extern void olpc_dt_build_devicetree(void);
 
+#else /* !CONFIG_OLPC */
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
-
-#endif /* !CONFIG_OLPC_OPENFIRMWARE */
+static inline void olpc_dt_build_devicetree(void) { }
+#endif /* !CONFIG_OLPC */
 
 #endif /* _ASM_X86_OLPC_OFW_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 6f1b7331313f..ade619ff9e2a 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,11 +15,7 @@
  */
 #define __PAGE_OFFSET           _AC(CONFIG_PAGE_OFFSET, UL)
 
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER    0
-#else
 #define THREAD_ORDER    1
-#endif
 #define THREAD_SIZE     (PAGE_SIZE << THREAD_ORDER)
 
 #define STACKFAULT_STACK 0
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index a667f24c7254..bce688d54c12 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -2,13 +2,14 @@
 #define _ASM_X86_PAGE_DEFS_H
 
 #include <linux/const.h>
+#include <linux/types.h>
 
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT      12
 #define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK       (~(PAGE_SIZE-1))
 
-#define __PHYSICAL_MASK         ((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __PHYSICAL_MASK         ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
 #define __VIRTUAL_MASK          ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
 /* Cast PAGE_MASK to a signed type so that it is sign-extended if
@@ -45,11 +46,15 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
+static inline phys_addr_t get_max_mapped(void)
+{
+        return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
+}
+
 extern unsigned long init_memory_mapping(unsigned long start,
                                          unsigned long end);
 
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn,
-                                int acpi, int k8);
+extern void initmem_init(void);
 extern void free_initmem(void);
 
 #endif  /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5653f43d90e5..ebbc4d8ab170 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -105,14 +105,14 @@ static inline void write_cr8(unsigned long x)
 }
 #endif
 
-static inline void raw_safe_halt(void)
+static inline void arch_safe_halt(void)
 {
         PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
 
 static inline void halt(void)
 {
-        PVOP_VCALL0(pv_irq_ops.safe_halt);
+        PVOP_VCALL0(pv_irq_ops.halt);
 }
 
 static inline void wbinvd(void)
@@ -416,11 +416,6 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
         PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-                                            unsigned long start, unsigned long count)
-{
-        PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
-}
 static inline void paravirt_release_pmd(unsigned long pfn)
 {
         PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
@@ -440,6 +435,11 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr,
 {
         PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
 }
+static inline void pmd_update(struct mm_struct *mm, unsigned long addr,
+                              pmd_t *pmdp)
+{
+        PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp);
+}
 
 static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
                                     pte_t *ptep)
@@ -447,6 +447,12 @@ static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
         PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
 }
 
+static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr,
+                                    pmd_t *pmdp)
+{
+        PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp);
+}
+
 static inline pte_t __pte(pteval_t val)
 {
         pteval_t ret;
@@ -548,6 +554,19 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
                 PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+                              pmd_t *pmdp, pmd_t pmd)
+{
+        if (sizeof(pmdval_t) > sizeof(long))
+                /* 5 arg words */
+                pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd);
+        else
+                PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp,
+                            native_pmd_val(pmd));
+}
+#endif
+
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
         pmdval_t val = native_pmd_val(pmd);
@@ -829,32 +848,32 @@ static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
 #define __PV_IS_CALLEE_SAVE(func)                       \
         ((struct paravirt_callee_save) { func })
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline notrace unsigned long arch_local_save_flags(void)
 {
         return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
-static inline void raw_local_irq_restore(unsigned long f)
+static inline notrace void arch_local_irq_restore(unsigned long f)
 {
         PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
-static inline void raw_local_irq_disable(void)
+static inline notrace void arch_local_irq_disable(void)
 {
         PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
-static inline void raw_local_irq_enable(void)
+static inline notrace void arch_local_irq_enable(void)
 {
         PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
-static inline unsigned long __raw_local_irq_save(void)
+static inline notrace unsigned long arch_local_irq_save(void)
 {
         unsigned long f;
 
-        f = __raw_local_save_flags();
-        raw_local_irq_disable();
+        f = arch_local_save_flags();
+        arch_local_irq_disable();
         return f;
 }
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index db9ef5532341..82885099c869 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -255,7 +255,6 @@ struct pv_mmu_ops {
          */
         void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
         void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
-        void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
         void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
         void (*release_pte)(unsigned long pfn);
         void (*release_pmd)(unsigned long pfn);
@@ -266,10 +265,16 @@ struct pv_mmu_ops {
         void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
                            pte_t *ptep, pte_t pteval);
         void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+        void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
+                           pmd_t *pmdp, pmd_t pmdval);
         void (*pte_update)(struct mm_struct *mm, unsigned long addr,
                            pte_t *ptep);
         void (*pte_update_defer)(struct mm_struct *mm,
                                  unsigned long addr, pte_t *ptep);
+        void (*pmd_update)(struct mm_struct *mm, unsigned long addr,
+                           pmd_t *pmdp);
+        void (*pmd_update_defer)(struct mm_struct *mm,
+                                 unsigned long addr, pmd_t *pmdp);
 
         pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
                                         pte_t *ptep);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d395540ff894..d498943b906c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <asm/scatterlist.h>
 #include <asm/io.h>
+#include <asm/x86_init.h>
 
 #ifdef __KERNEL__
 
@@ -64,6 +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);
 
@@ -94,8 +96,36 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
-/* MSI arch hook */
-#define arch_setup_msi_irqs arch_setup_msi_irqs
+#ifdef CONFIG_PCI_MSI
+/* MSI arch specific hooks */
+static inline int x86_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+        return x86_msi.setup_msi_irqs(dev, nvec, type);
+}
+
+static inline void x86_teardown_msi_irqs(struct pci_dev *dev)
+{
+        x86_msi.teardown_msi_irqs(dev);
+}
+
+static inline void x86_teardown_msi_irq(unsigned int irq)
+{
+        x86_msi.teardown_msi_irq(irq);
+}
+#define arch_setup_msi_irqs x86_setup_msi_irqs
+#define arch_teardown_msi_irqs x86_teardown_msi_irqs
+#define arch_teardown_msi_irq x86_teardown_msi_irq
+/* implemented in arch/x86/kernel/apic/io_apic. */
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+void native_teardown_msi_irq(unsigned int irq);
+/* default to the implementation in drivers/lib/msi.c */
+#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev);
+#else
+#define native_setup_msi_irqs           NULL
+#define native_teardown_msi_irq         NULL
+#define default_teardown_msi_irqs       NULL
+#endif
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
@@ -105,8 +135,6 @@ extern void pci_iommu_alloc(void);
 #include "pci_64.h"
 #endif
 
-void dma32_reserve_bootmem(void);
-
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 49c7219826f9..704526734bef 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -47,6 +47,7 @@ enum pci_bf_sort_state {
 extern unsigned int pcibios_max_latency;
 
 void pcibios_resource_survey(void);
+void pcibios_set_cache_line_size(void);
 
 /* pci-pc.c */
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index cd28f9ad910d..a0a9779084d1 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -45,12 +45,28 @@
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
-#define __percpu_arg(x)         "%%"__stringify(__percpu_seg)":%P" #x
+#define __percpu_prefix         "%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset         percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)                             \
+({                                                      \
+        unsigned long tcp_ptr__;                        \
+        __verify_pcpu_ptr(ptr);                         \
+        asm volatile("add " __percpu_arg(1) ", %0"      \
+                     : "=r" (tcp_ptr__)                 \
+                     : "m" (this_cpu_off), "0" (ptr));  \
+        (typeof(*(ptr)) __kernel __force *)tcp_ptr__;   \
+})
 #else
-#define __percpu_arg(x)         "%P" #x
+#define __percpu_prefix         ""
 #endif
 
+#define __percpu_arg(x)         __percpu_prefix "%P" #x
+
 /*
  * Initialized pointers to per-cpu variables needed for the boot
  * processor need to use these macros to get the proper address
@@ -216,6 +232,125 @@ 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("\n\tmov "__percpu_arg(1)",%%al"                    \
+                    "\n1:\tcmpxchgb %2, "__percpu_arg(1)                \
+                    "\n\tjnz 1b"                                        \
+                            : "=&a" (pxo_ret__), "+m" (var)             \
+                            : "q" (pxo_new__)                           \
+                            : "memory");                                \
+                break;                                                  \
+        case 2:                                                         \
+                asm("\n\tmov "__percpu_arg(1)",%%ax"                    \
+                    "\n1:\tcmpxchgw %2, "__percpu_arg(1)                \
+                    "\n\tjnz 1b"                                        \
+                            : "=&a" (pxo_ret__), "+m" (var)             \
+                            : "r" (pxo_new__)                           \
+                            : "memory");                                \
+                break;                                                  \
+        case 4:                                                         \
+                asm("\n\tmov "__percpu_arg(1)",%%eax"                   \
+                    "\n1:\tcmpxchgl %2, "__percpu_arg(1)                \
+                    "\n\tjnz 1b"                                        \
+                            : "=&a" (pxo_ret__), "+m" (var)             \
+                            : "r" (pxo_new__)                           \
+                            : "memory");                                \
+                break;                                                  \
+        case 8:                                                         \
+                asm("\n\tmov "__percpu_arg(1)",%%rax"                   \
+                    "\n1:\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
@@ -253,6 +388,12 @@ 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))
@@ -272,6 +413,9 @@ 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 irqsafe_cpu_add_1(pcp, val)     percpu_add_op((pcp), val)
 #define irqsafe_cpu_add_2(pcp, val)     percpu_add_op((pcp), val)
@@ -285,6 +429,49 @@ 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)
+
+#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 */
+
+#ifdef CONFIG_X86_CMPXCHG64
+#define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)                   \
+({                                                                      \
+        char __ret;                                                     \
+        typeof(o1) __o1 = o1;                                           \
+        typeof(o1) __n1 = n1;                                           \
+        typeof(o2) __o2 = o2;                                           \
+        typeof(o2) __n2 = n2;                                           \
+        typeof(o2) __dummy = n2;                                        \
+        asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"       \
+                    : "=a"(__ret), "=m" (pcp1), "=d"(__dummy)           \
+                    :  "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2));     \
+        __ret;                                                          \
+})
+
+#define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)         percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+#define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)           percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+#define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)        percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+#endif /* CONFIG_X86_CMPXCHG64 */
 
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -297,6 +484,7 @@ 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)
@@ -304,11 +492,48 @@ 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_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_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)
+#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)
+
+/*
+ * Pretty complex macro to generate cmpxchg16 instruction.  The instruction
+ * is not supported on early AMD64 processors so we must be able to emulate
+ * it in software.  The address used in the cmpxchg16 instruction must be
+ * aligned to a 16 byte boundary.
+ */
+#ifdef CONFIG_SMP
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP3
+#else
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2
+#endif
+#define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)                  \
+({                                                                      \
+        char __ret;                                                     \
+        typeof(o1) __o1 = o1;                                           \
+        typeof(o1) __n1 = n1;                                           \
+        typeof(o2) __o2 = o2;                                           \
+        typeof(o2) __n2 = n2;                                           \
+        typeof(o2) __dummy;                                             \
+        alternative_io(CMPXCHG16B_EMU_CALL,                             \
+                       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",  \
+                       X86_FEATURE_CX16,                                \
+                       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),         \
+                       "S" (&pcp1), "b"(__n1), "c"(__n2),               \
+                       "a"(__o1), "d"(__o2) : "memory");                \
+        __ret;                                                          \
+})
+
+#define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)         percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+#define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)           percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+#define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)        percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
 
 #endif
 
@@ -322,6 +547,33 @@ do {									\
         old__;                                                          \
 })
 
+static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+                        const unsigned long __percpu *addr)
+{
+        unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+        return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+}
+
+static inline int x86_this_cpu_variable_test_bit(int nr,
+                        const unsigned long __percpu *addr)
+{
+        int oldbit;
+
+        asm volatile("bt "__percpu_arg(2)",%1\n\t"
+                        "sbb %0,%0"
+                        : "=r" (oldbit)
+                        : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+        return oldbit;
+}
+
+#define x86_this_cpu_test_bit(nr, addr)                 \
+        (__builtin_constant_p((nr))                     \
+         ? x86_this_cpu_constant_test_bit((nr), (addr)) \
+         : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6e742cc4251b..d9d4dae305f6 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -111,20 +111,20 @@ union cpuid10_edx {
 #define X86_PMC_IDX_FIXED_BTS                           (X86_PMC_IDX_FIXED + 16)
 
 /* IbsFetchCtl bits/masks */
-#define IBS_FETCH_RAND_EN               (1ULL<<57)
-#define IBS_FETCH_VAL                   (1ULL<<49)
-#define IBS_FETCH_ENABLE                (1ULL<<48)
-#define IBS_FETCH_CNT                   0xFFFF0000ULL
-#define IBS_FETCH_MAX_CNT               0x0000FFFFULL
+#define IBS_FETCH_RAND_EN       (1ULL<<57)
+#define IBS_FETCH_VAL           (1ULL<<49)
+#define IBS_FETCH_ENABLE        (1ULL<<48)
+#define IBS_FETCH_CNT           0xFFFF0000ULL
+#define IBS_FETCH_MAX_CNT       0x0000FFFFULL
 
 /* IbsOpCtl bits */
-#define IBS_OP_CNT_CTL                  (1ULL<<19)
-#define IBS_OP_VAL                      (1ULL<<18)
-#define IBS_OP_ENABLE                   (1ULL<<17)
-#define IBS_OP_MAX_CNT                  0x0000FFFFULL
+#define IBS_OP_CNT_CTL          (1ULL<<19)
+#define IBS_OP_VAL              (1ULL<<18)
+#define IBS_OP_ENABLE           (1ULL<<17)
+#define IBS_OP_MAX_CNT          0x0000FFFFULL
+#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
@@ -155,7 +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 def500776b16..56fd9e3abbda 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -1,5 +1,5 @@
 /*
- * Netburst Perfomance Events (P4, old Xeon)
+ * Netburst Performance Events (P4, old Xeon)
  */
 
 #ifndef PERF_EVENT_P4_H
@@ -9,7 +9,7 @@
 #include <linux/bitops.h>
 
 /*
- * NetBurst has perfomance MSRs shared between
+ * NetBurst has performance MSRs shared between
  * threads if HT is turned on, ie for both logical
  * processors (mem: in turn in Atom with HT support
  * perf-MSRs are not shared and every thread has its
@@ -20,6 +20,10 @@
 #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 ARCH_P4_UNFLAGGED_BIT   ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1))
+
 #define P4_ESCR_EVENT_MASK      0x7e000000U
 #define P4_ESCR_EVENT_SHIFT     25
 #define P4_ESCR_EVENTMASK_MASK  0x01fffe00U
@@ -36,19 +40,6 @@
 #define P4_ESCR_EMASK(v)        ((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)          ((v) << P4_ESCR_TAG_SHIFT)
 
-/* Non HT mask */
-#define P4_ESCR_MASK                    \
-        (P4_ESCR_EVENT_MASK     |       \
-        P4_ESCR_EVENTMASK_MASK  |       \
-        P4_ESCR_TAG_MASK        |       \
-        P4_ESCR_TAG_ENABLE      |       \
-        P4_ESCR_T0_OS           |       \
-        P4_ESCR_T0_USR)
-
-/* HT mask */
-#define P4_ESCR_MASK_HT                 \
-        (P4_ESCR_MASK | P4_ESCR_T1_OS | P4_ESCR_T1_USR)
-
 #define P4_CCCR_OVF                     0x80000000U
 #define P4_CCCR_CASCADE                 0x40000000U
 #define P4_CCCR_OVF_PMI_T0              0x04000000U
@@ -70,23 +61,6 @@
 #define P4_CCCR_THRESHOLD(v)            ((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)                 ((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
-/* Non HT mask */
-#define P4_CCCR_MASK                            \
-        (P4_CCCR_OVF                    |       \
-        P4_CCCR_CASCADE                 |       \
-        P4_CCCR_OVF_PMI_T0              |       \
-        P4_CCCR_FORCE_OVF               |       \
-        P4_CCCR_EDGE                    |       \
-        P4_CCCR_THRESHOLD_MASK          |       \
-        P4_CCCR_COMPLEMENT              |       \
-        P4_CCCR_COMPARE                 |       \
-        P4_CCCR_ESCR_SELECT_MASK        |       \
-        P4_CCCR_ENABLE)
-
-/* HT mask */
-#define P4_CCCR_MASK_HT                         \
-        (P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
-
 #define P4_GEN_ESCR_EMASK(class, name, bit)     \
         class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)          class##__##name
@@ -127,6 +101,28 @@
 #define P4_CONFIG_HT_SHIFT              63
 #define P4_CONFIG_HT                    (1ULL << P4_CONFIG_HT_SHIFT)
 
+/*
+ * The bits we allow to pass for RAW events
+ */
+#define P4_CONFIG_MASK_ESCR             \
+        P4_ESCR_EVENT_MASK      |       \
+        P4_ESCR_EVENTMASK_MASK  |       \
+        P4_ESCR_TAG_MASK        |       \
+        P4_ESCR_TAG_ENABLE
+
+#define P4_CONFIG_MASK_CCCR             \
+        P4_CCCR_EDGE            |       \
+        P4_CCCR_THRESHOLD_MASK  |       \
+        P4_CCCR_COMPLEMENT      |       \
+        P4_CCCR_COMPARE         |       \
+        P4_CCCR_THREAD_ANY      |       \
+        P4_CCCR_RESERVED
+
+/* some dangerous bits are reserved for kernel internals */
+#define P4_CONFIG_MASK                                    \
+        (p4_config_pack_escr(P4_CONFIG_MASK_ESCR))      | \
+        (p4_config_pack_cccr(P4_CONFIG_MASK_CCCR))
+
 static inline bool p4_is_event_cascaded(u64 config)
 {
         u32 cccr = p4_config_unpack_cccr(config);
@@ -752,14 +748,6 @@ 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
  */
@@ -796,5 +784,60 @@ 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/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 271de94c3810..b4389a468fb6 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -92,7 +92,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
-                                  unsigned long adddress)
+                                  unsigned long address)
 {
         ___pmd_free_tlb(tlb, pmd);
 }
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 2334982b339e..98391db840c6 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -46,6 +46,15 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_SMP
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
+{
+        return __pmd(xchg((pmdval_t *)xp, 0));
+}
+#else
+#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
+#endif
+
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
  * split up the 29 bits of offset into this range:
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 177b0165ea01..effff47a3c82 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -69,8 +69,6 @@ static inline void native_pmd_clear(pmd_t *pmd)
 
 static inline void pud_clear(pud_t *pudp)
 {
-        unsigned long pgd;
-
         set_pud(pudp, __pud(0));
 
         /*
@@ -79,13 +77,10 @@ static inline void pud_clear(pud_t *pudp)
          * section 8.1: in PAE mode we explicitly have to flush the
          * TLB via cr3 if the top-level pgd is changed...
          *
-         * Make sure the pud entry we're updating is within the
-         * current pgd to avoid unnecessary TLB flushes.
+         * Currently all places where pud_clear() is called either have
+         * flush_tlb_mm() followed or don't need TLB flush (x86_64 code or
+         * pud_clear_bad()), so we don't need TLB flush here.
          */
-        pgd = read_cr3();
-        if (__pa(pudp) >= pgd && __pa(pudp) <
-            (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
-                write_cr3(pgd);
 }
 
 #ifdef CONFIG_SMP
@@ -104,6 +99,29 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
+#ifdef CONFIG_SMP
+union split_pmd {
+        struct {
+                u32 pmd_low;
+                u32 pmd_high;
+        };
+        pmd_t pmd;
+};
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
+{
+        union split_pmd res, *orig = (union split_pmd *)pmdp;
+
+        /* xchg acts as a barrier before setting of the high bits */
+        res.pmd_low = xchg(&orig->pmd_low, 0);
+        res.pmd_high = orig->pmd_high;
+        orig->pmd_high = 0;
+
+        return res.pmd;
+}
+#else
+#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
+#endif
+
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a34c785c5a63..18601c86fab1 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,11 +28,14 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
 
+extern struct mm_struct *pgd_page_get_mm(struct page *page);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
 #define set_pte(ptep, pte)              native_set_pte(ptep, pte)
 #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
+#define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd)
 
 #define set_pte_atomic(ptep, pte)                                       \
         native_set_pte_atomic(ptep, pte)
@@ -57,6 +60,8 @@ extern struct list_head pgd_list;
 
 #define pte_update(mm, addr, ptep)              do { } while (0)
 #define pte_update_defer(mm, addr, ptep)        do { } while (0)
+#define pmd_update(mm, addr, ptep)              do { } while (0)
+#define pmd_update_defer(mm, addr, ptep)        do { } while (0)
 
 #define pgd_val(x)      native_pgd_val(x)
 #define __pgd(x)        native_make_pgd(x)
@@ -92,6 +97,11 @@ static inline int pte_young(pte_t pte)
         return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+static inline int pmd_young(pmd_t pmd)
+{
+        return pmd_flags(pmd) & _PAGE_ACCESSED;
+}
+
 static inline int pte_write(pte_t pte)
 {
         return pte_flags(pte) & _PAGE_RW;
@@ -140,6 +150,23 @@ static inline int pmd_large(pmd_t pte)
                 (_PAGE_PSE | _PAGE_PRESENT);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+        return pmd_val(pmd) & _PAGE_SPLITTING;
+}
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+        return pmd_val(pmd) & _PAGE_PSE;
+}
+
+static inline int has_transparent_hugepage(void)
+{
+        return cpu_has_pse;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
 {
         pteval_t v = native_pte_val(pte);
@@ -214,6 +241,55 @@ static inline pte_t pte_mkspecial(pte_t pte)
         return pte_set_flags(pte, _PAGE_SPECIAL);
 }
 
+static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
+{
+        pmdval_t v = native_pmd_val(pmd);
+
+        return __pmd(v | set);
+}
+
+static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
+{
+        pmdval_t v = native_pmd_val(pmd);
+
+        return __pmd(v & ~clear);
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+        return pmd_clear_flags(pmd, _PAGE_ACCESSED);
+}
+
+static inline pmd_t pmd_wrprotect(pmd_t pmd)
+{
+        return pmd_clear_flags(pmd, _PAGE_RW);
+}
+
+static inline pmd_t pmd_mkdirty(pmd_t pmd)
+{
+        return pmd_set_flags(pmd, _PAGE_DIRTY);
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+        return pmd_set_flags(pmd, _PAGE_PSE);
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+        return pmd_set_flags(pmd, _PAGE_ACCESSED);
+}
+
+static inline pmd_t pmd_mkwrite(pmd_t pmd)
+{
+        return pmd_set_flags(pmd, _PAGE_RW);
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+        return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
@@ -254,6 +330,16 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
         return __pte(val);
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+        pmdval_t val = pmd_val(pmd);
+
+        val &= _HPAGE_CHG_MASK;
+        val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+
+        return __pmd(val);
+}
+
 /* mprotect needs to preserve PAT bits when updating vm_page_prot */
 #define pgprot_modify pgprot_modify
 static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
@@ -348,7 +434,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pmd_page(pmd)   pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd)   pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
 
 /*
  * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
@@ -522,12 +608,26 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
         return res;
 }
 
+static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp)
+{
+        pmd_t res = *pmdp;
+
+        native_pmd_clear(pmdp);
+        return res;
+}
+
 static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
                                      pte_t *ptep , pte_t pte)
 {
         native_set_pte(ptep, pte);
 }
 
+static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
+                                     pmd_t *pmdp , pmd_t pmd)
+{
+        native_set_pmd(pmdp, pmd);
+}
+
 #ifndef CONFIG_PARAVIRT
 /*
  * Rules for using pte_update - it must be called after any PTE update which
@@ -603,6 +703,51 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
         pte_update(mm, addr, ptep);
 }
 
+#define flush_tlb_fix_spurious_fault(vma, address)
+
+#define mk_pmd(page, pgprot)   pfn_pmd(page_to_pfn(page), (pgprot))
+
+#define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+                                 unsigned long address, pmd_t *pmdp,
+                                 pmd_t entry, int dirty);
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+                                     unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+                                  unsigned long address, pmd_t *pmdp);
+
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+                                 unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMD_WRITE
+static inline int pmd_write(pmd_t pmd)
+{
+        return pmd_flags(pmd) & _PAGE_RW;
+}
+
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr,
+                                       pmd_t *pmdp)
+{
+        pmd_t pmd = native_pmdp_get_and_clear(pmdp);
+        pmd_update(mm, addr, pmdp);
+        return pmd;
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+                                      unsigned long addr, pmd_t *pmdp)
+{
+        clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
+        pmd_update(mm, addr, pmdp);
+}
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index f686f49e8b7b..0c92113c4cb6 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -26,7 +26,7 @@ struct mm_struct;
 struct vm_area_struct;
 
 extern pgd_t swapper_pg_dir[1024];
-extern pgd_t trampoline_pg_dir[1024];
+extern pgd_t initial_page_table[1024];
 
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
@@ -49,24 +49,14 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 #endif
 
 #if defined(CONFIG_HIGHPTE)
-#define __KM_PTE                        \
-        (in_nmi() ? KM_NMI_PTE :        \
-         in_irq() ? KM_IRQ_PTE :        \
-         KM_PTE0)
 #define pte_offset_map(dir, address)                                    \
-        ((pte_t *)kmap_atomic(pmd_page(*(dir)), __KM_PTE) +             \
+        ((pte_t *)kmap_atomic(pmd_page(*(dir))) +               \
          pte_index((address)))
-#define pte_offset_map_nested(dir, address)                             \
-        ((pte_t *)kmap_atomic(pmd_page(*(dir)), KM_PTE1) +              \
-         pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE)
-#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
+#define pte_unmap(pte) kunmap_atomic((pte))
 #else
 #define pte_offset_map(dir, address)                                    \
         ((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
-#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address))
 #define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
 #endif
 
 /* Clear a kernel PTE and flush it from the TLB */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 076052cd62be..975f709e09ae 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -59,6 +59,16 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
         native_set_pte(ptep, pte);
 }
 
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+        *pmdp = pmd;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+        native_set_pmd(pmd, native_make_pmd(0));
+}
+
 static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 {
 #ifdef CONFIG_SMP
@@ -72,14 +82,17 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #endif
 }
 
-static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-        *pmdp = pmd;
-}
-
-static inline void native_pmd_clear(pmd_t *pmd)
+static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 {
-        native_set_pmd(pmd, native_make_pmd(0));
+#ifdef CONFIG_SMP
+        return native_make_pmd(xchg(&xp->pmd, 0));
+#else
+        /* native_local_pmdp_get_and_clear,
+           but duplicated because of cyclic dependency */
+        pmd_t ret = *xp;
+        native_pmd_clear(xp);
+        return ret;
+#endif
 }
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
@@ -102,6 +115,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
         native_set_pgd(pgd, native_make_pgd(0));
 }
 
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
@@ -125,9 +140,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 /* x86-64 always has all page tables mapped. */
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
-#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
 #define pte_unmap(pte) ((void)(pte))/* NOP */
-#define pte_unmap_nested(pte) ((void)(pte)) /* NOP */
 
 #define update_mmu_cache(vma, address, ptep) do { } while (0)
 
@@ -168,6 +181,7 @@ extern void cleanup_highmap(void);
 #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
 
 #define __HAVE_ARCH_PTE_SAME
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d1f4a760be23..d56187c6b838 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -22,6 +22,7 @@
 #define _PAGE_BIT_PAT_LARGE     12      /* On 2MB or 1GB pages */
 #define _PAGE_BIT_SPECIAL       _PAGE_BIT_UNUSED1
 #define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
+#define _PAGE_BIT_SPLITTING     _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
@@ -45,6 +46,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL   (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST  (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING)
 #define __HAVE_ARCH_PTE_SPECIAL
 
 #ifdef CONFIG_KMEMCHECK
@@ -70,6 +72,7 @@
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK  (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |         \
                          _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 #define _PAGE_CACHE_MASK        (_PAGE_PCD | _PAGE_PWT)
 #define _PAGE_CACHE_WB          (0)
@@ -296,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);
diff --git a/arch/x86/include/asm/probe_roms.h b/arch/x86/include/asm/probe_roms.h
new file mode 100644
index 000000000000..4950a0b1d09c
--- /dev/null
+++ b/arch/x86/include/asm/probe_roms.h
@@ -0,0 +1,8 @@
+#ifndef _PROBE_ROMS_H_
+#define _PROBE_ROMS_H_
+struct pci_dev;
+
+extern void __iomem *pci_map_biosrom(struct pci_dev *pdev);
+extern void pci_unmap_biosrom(void __iomem *rom);
+extern size_t pci_biosrom_size(struct pci_dev *pdev);
+#endif
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 7a3e836eb2a9..59ab4dffa377 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -7,7 +7,7 @@
  */
 #define X86_EFLAGS_CF   0x00000001 /* Carry Flag */
 #define X86_EFLAGS_PF   0x00000004 /* Parity Flag */
-#define X86_EFLAGS_AF   0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_AF   0x00000010 /* Auxiliary carry Flag */
 #define X86_EFLAGS_ZF   0x00000040 /* Zero Flag */
 #define X86_EFLAGS_SF   0x00000080 /* Sign Flag */
 #define X86_EFLAGS_TF   0x00000100 /* Trap Flag */
@@ -60,6 +60,7 @@
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE    0x00002000 /* enable VMX virtualization */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
+#define X86_CR4_SMEP    0x00100000 /* enable SMEP support */
 
 /*
  * x86-64 Task Priority Register, CR8
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ebaa04a8d3af..b844edc69fe9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -94,10 +94,6 @@ struct cpuinfo_x86 {
         int                     x86_cache_alignment;    /* In bytes */
         int                     x86_power;
         unsigned long           loops_per_jiffy;
-#ifdef CONFIG_SMP
-        /* cpus sharing the last level cache: */
-        cpumask_var_t           llc_shared_map;
-#endif
         /* cpuid returned max cores value: */
         u16                      x86_max_cores;
         u16                     apicid;
@@ -110,6 +106,8 @@ struct cpuinfo_x86 {
         u16                     phys_proc_id;
         /* Core id: */
         u16                     cpu_core_id;
+        /* Compute unit id */
+        u8                      compute_unit_id;
         /* Index into per_cpu list: */
         u16                     cpu_index;
 #endif
@@ -139,10 +137,9 @@ 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;
@@ -606,7 +603,7 @@ extern unsigned long		mmu_cr4_features;
 
 static inline void set_in_cr4(unsigned long mask)
 {
-        unsigned cr4;
+        unsigned long cr4;
 
         mmu_cr4_features |= mask;
         cr4 = read_cr4();
@@ -616,7 +613,7 @@ static inline void set_in_cr4(unsigned long mask)
 
 static inline void clear_in_cr4(unsigned long mask)
 {
-        unsigned cr4;
+        unsigned long cr4;
 
         mmu_cr4_features &= ~mask;
         cr4 = read_cr4();
@@ -761,35 +758,13 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_c1e_mask(void);
+extern void init_amd_e400_c1e_mask(void);
 
 extern unsigned long            boot_option_idle_override;
-extern unsigned long            idle_halt;
-extern unsigned long            idle_nomwait;
-extern bool                     c1e_detected;
+extern bool                     amd_e400_c1e_detected;
 
-/*
- * on systems with caches, caches must be flashed as the absolute
- * last instruction before going into a suspended halt.  Otherwise,
- * dirty data can linger in the cache and become stale on resume,
- * leading to strange errors.
- *
- * perform a variety of operations to guarantee that the compiler
- * will not reorder instructions.  wbinvd itself is serializing
- * so the processor will not reorder.
- *
- * Systems without cache can just go into halt.
- */
-static inline void wbinvd_halt(void)
-{
-        mb();
-        /* check for clflush to determine if wbinvd is legal */
-        if (cpu_has_clflush)
-                asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
-        else
-                while (1)
-                        halt();
-}
+enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
+                         IDLE_POLL, IDLE_FORCE_MWAIT};
 
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
@@ -927,7 +902,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 /*
  * The below -8 is to reserve 8 bytes on top of the ring0 stack.
  * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessable even if the CPU haven't stored the SS/ESP registers
+ * is accessible even if the CPU haven't stored the SS/ESP registers
  * on the stack (interrupt gate does not save these registers
  * when switching to the same priv ring).
  * Therefore beware: accessing the ss/esp fields of the
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
new file mode 100644
index 000000000000..971e0b46446e
--- /dev/null
+++ b/arch/x86/include/asm/prom.h
@@ -0,0 +1,69 @@
+/*
+ * Definitions for Device tree / OpenFirmware handling on X86
+ *
+ * based on arch/powerpc/include/asm/prom.h which is
+ *         Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ * 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.
+ */
+
+#ifndef _ASM_X86_PROM_H
+#define _ASM_X86_PROM_H
+#ifndef __ASSEMBLY__
+
+#include <linux/of.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#include <asm/irq.h>
+#include <asm/atomic.h>
+#include <asm/setup.h>
+#include <asm/irq_controller.h>
+
+#ifdef CONFIG_OF
+extern int of_ioapic;
+extern u64 initial_dtb;
+extern void add_dtb(u64 data);
+extern void x86_add_irq_domains(void);
+void __cpuinit x86_of_pci_init(void);
+void x86_dtb_init(void);
+
+static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
+{
+        return pdev ? pdev->dev.of_node : NULL;
+}
+
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+        return pci_device_to_OF_node(bus->self);
+}
+
+#else
+static inline void add_dtb(u64 data) { }
+static inline void x86_add_irq_domains(void) { }
+static inline void x86_of_pci_init(void) { }
+static inline void x86_dtb_init(void) { }
+#define of_ioapic 0
+#endif
+
+extern char cmd_line[COMMAND_LINE_SIZE];
+
+#define pci_address_to_pio pci_address_to_pio
+unsigned long pci_address_to_pio(phys_addr_t addr);
+
+/**
+ * irq_dispose_mapping - Unmap an interrupt
+ * @virq: linux virq number of the interrupt to unmap
+ *
+ * FIXME: We really should implement proper virq handling like power,
+ * but that's going to be major surgery.
+ */
+static inline void irq_dispose_mapping(unsigned int virq) { }
+
+#define HAVE_ARCH_DEVTREE_FIXUPS
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 52b098a6eebb..7b0a55a88851 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -31,7 +31,7 @@
 #define R12 24
 #define RBP 32
 #define RBX 40
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here*/
 #define R11 48
 #define R10 56
 #define R9 64
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 78cd1ea94500..94e7618fcac8 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -73,7 +73,7 @@ struct pt_regs {
         unsigned long r12;
         unsigned long rbp;
         unsigned long rbx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
+/* arguments: non interrupts/non tracing syscalls only save up to here*/
         unsigned long r11;
         unsigned long r10;
         unsigned long r9;
@@ -103,7 +103,7 @@ struct pt_regs {
         unsigned long r12;
         unsigned long bp;
         unsigned long bx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
+/* arguments: non interrupts/non tracing syscalls only save up to here*/
         unsigned long r11;
         unsigned long r10;
         unsigned long r9;
@@ -136,6 +136,7 @@ struct cpuinfo_x86;
 struct task_struct;
 
 extern unsigned long profile_pc(struct pt_regs *regs);
+#define profile_pc profile_pc
 
 extern unsigned long
 convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
@@ -202,20 +203,11 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 #endif
 }
 
-static inline unsigned long instruction_pointer(struct pt_regs *regs)
-{
-        return regs->ip;
-}
-
-static inline unsigned long frame_pointer(struct pt_regs *regs)
-{
-        return regs->bp;
-}
+#define GET_IP(regs) ((regs)->ip)
+#define GET_FP(regs) ((regs)->bp)
+#define GET_USP(regs) ((regs)->sp)
 
-static inline unsigned long user_stack_pointer(struct pt_regs *regs)
-{
-        return regs->sp;
-}
+#include <asm-generic/ptrace.h>
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index cd02f324aa6b..a518c0a45044 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -11,5 +11,49 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
                             struct pvclock_vcpu_time_info *vcpu,
                             struct timespec *ts);
+void pvclock_resume(void);
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+        u64 product;
+#ifdef __i386__
+        u32 tmp1, tmp2;
+#else
+        ulong tmp;
+#endif
+
+        if (shift < 0)
+                delta >>= -shift;
+        else
+                delta <<= shift;
+
+#ifdef __i386__
+        __asm__ (
+                "mul  %5       ; "
+                "mov  %4,%%eax ; "
+                "mov  %%edx,%4 ; "
+                "mul  %5       ; "
+                "xor  %5,%5    ; "
+                "add  %4,%%eax ; "
+                "adc  %5,%%edx ; "
+                : "=A" (product), "=r" (tmp1), "=r" (tmp2)
+                : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif defined(__x86_64__)
+        __asm__ (
+                "mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+                : [lo]"=a"(product),
+                  [hi]"=d"(tmp)
+                : "0"(delta),
+                  [mul_frac]"rm"((u64)mul_frac));
+#else
+#error implement me!
+#endif
+
+        return product;
+}
 
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 562d4fd31ba8..3250e3d605d9 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -18,7 +18,10 @@ extern struct machine_ops machine_ops;
 
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
-void machine_real_restart(const unsigned char *code, int length);
+void machine_real_restart(unsigned int type);
+/* These must match dispatch_table in reboot_32.S */
+#define MRR_BIOS        0
+#define MRR_APM         1
 
 typedef void (*nmi_shootdown_cb)(int, struct die_args*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index d1e41b0f9b60..df4cd32b4cc6 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -37,26 +37,9 @@
 #endif
 
 #ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/lockdep.h>
 #include <asm/asm.h>
 
-struct rwsem_waiter;
-
-extern asmregparm struct rw_semaphore *
- rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *
- rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
- * the semaphore definition
- *
  * The bias values and the counter type limits the number of
  * potential readers/writers to 32767 for 32 bits and 2147483647
  * for 64 bits.
@@ -74,43 +57,6 @@ extern asmregparm struct rw_semaphore *
 #define RWSEM_ACTIVE_READ_BIAS          RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS         (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-typedef signed long rwsem_count_t;
-
-struct rw_semaphore {
-        rwsem_count_t           count;
-        spinlock_t              wait_lock;
-        struct list_head        wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-        struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-
-#define __RWSEM_INITIALIZER(name)                               \
-{                                                               \
-        RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-        LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name)                                     \
-        struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-                         struct lock_class_key *key);
-
-#define init_rwsem(sem)                                         \
-do {                                                            \
-        static struct lock_class_key __key;                     \
-                                                                \
-        __init_rwsem((sem), #sem, &__key);                      \
-} while (0)
-
 /*
  * lock for reading
  */
@@ -133,7 +79,7 @@ static inline void __down_read(struct rw_semaphore *sem)
  */
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-        rwsem_count_t result, tmp;
+        long result, tmp;
         asm volatile("# beginning __down_read_trylock\n\t"
                      "  mov          %0,%1\n\t"
                      "1:\n\t"
@@ -155,7 +101,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
  */
 static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
-        rwsem_count_t tmp;
+        long tmp;
         asm volatile("# beginning down_write\n\t"
                      LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* adds 0xffff0001, returns the old value */
@@ -180,9 +126,8 @@ static inline void __down_write(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-        rwsem_count_t ret = cmpxchg(&sem->count,
-                                    RWSEM_UNLOCKED_VALUE,
-                                    RWSEM_ACTIVE_WRITE_BIAS);
+        long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+                           RWSEM_ACTIVE_WRITE_BIAS);
         if (ret == RWSEM_UNLOCKED_VALUE)
                 return 1;
         return 0;
@@ -193,7 +138,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
  */
 static inline void __up_read(struct rw_semaphore *sem)
 {
-        rwsem_count_t tmp;
+        long tmp;
         asm volatile("# beginning __up_read\n\t"
                      LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* subtracts 1, returns the old value */
@@ -211,7 +156,7 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-        rwsem_count_t tmp;
+        long tmp;
         asm volatile("# beginning __up_write\n\t"
                      LOCK_PREFIX "  xadd      %1,(%2)\n\t"
                      /* subtracts 0xffff0001, returns the old value */
@@ -247,8 +192,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 /*
  * implement atomic add functionality
  */
-static inline void rwsem_atomic_add(rwsem_count_t delta,
-                                    struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 {
         asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
                      : "+m" (sem->count)
@@ -258,10 +202,9 @@ static inline void rwsem_atomic_add(rwsem_count_t delta,
 /*
  * implement exchange and add functionality
  */
-static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
-                                                struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 {
-        rwsem_count_t tmp = delta;
+        long tmp = delta;
 
         asm volatile(LOCK_PREFIX "xadd %0,%1"
                      : "+r" (tmp), "+m" (sem->count)
@@ -270,10 +213,5 @@ static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
         return tmp + delta;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-        return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 14e0ed86a6f9..cd84f7208f76 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -1,14 +1,16 @@
 #ifndef _ASM_X86_SEGMENT_H
 #define _ASM_X86_SEGMENT_H
 
+#include <linux/const.h>
+
 /* Constructor for a conventional segment GDT (or LDT) entry */
 /* This is a macro so it can be used in initializers */
 #define GDT_ENTRY(flags, base, limit)                   \
-        ((((base)  & 0xff000000ULL) << (56-24)) |       \
-         (((flags) & 0x0000f0ffULL) << 40) |            \
-         (((limit) & 0x000f0000ULL) << (48-16)) |       \
-         (((base)  & 0x00ffffffULL) << 16) |            \
-         (((limit) & 0x0000ffffULL)))
+        ((((base)  & _AC(0xff000000,ULL)) << (56-24)) | \
+         (((flags) & _AC(0x0000f0ff,ULL)) << 40) |      \
+         (((limit) & _AC(0x000f0000,ULL)) << (48-16)) | \
+         (((base)  & _AC(0x00ffffff,ULL)) << 16) |      \
+         (((limit) & _AC(0x0000ffff,ULL))))
 
 /* Simple and small GDT entries for booting only */
 
@@ -73,31 +75,31 @@
 
 #define GDT_ENTRY_DEFAULT_USER_DS       15
 
-#define GDT_ENTRY_KERNEL_BASE   12
+#define GDT_ENTRY_KERNEL_BASE           (12)
 
-#define GDT_ENTRY_KERNEL_CS             (GDT_ENTRY_KERNEL_BASE + 0)
+#define GDT_ENTRY_KERNEL_CS             (GDT_ENTRY_KERNEL_BASE+0)
 
-#define GDT_ENTRY_KERNEL_DS             (GDT_ENTRY_KERNEL_BASE + 1)
+#define GDT_ENTRY_KERNEL_DS             (GDT_ENTRY_KERNEL_BASE+1)
 
-#define GDT_ENTRY_TSS                   (GDT_ENTRY_KERNEL_BASE + 4)
-#define GDT_ENTRY_LDT                   (GDT_ENTRY_KERNEL_BASE + 5)
+#define GDT_ENTRY_TSS                   (GDT_ENTRY_KERNEL_BASE+4)
+#define GDT_ENTRY_LDT                   (GDT_ENTRY_KERNEL_BASE+5)
 
-#define GDT_ENTRY_PNPBIOS_BASE          (GDT_ENTRY_KERNEL_BASE + 6)
-#define GDT_ENTRY_APMBIOS_BASE          (GDT_ENTRY_KERNEL_BASE + 11)
+#define GDT_ENTRY_PNPBIOS_BASE          (GDT_ENTRY_KERNEL_BASE+6)
+#define GDT_ENTRY_APMBIOS_BASE          (GDT_ENTRY_KERNEL_BASE+11)
 
-#define GDT_ENTRY_ESPFIX_SS             (GDT_ENTRY_KERNEL_BASE + 14)
-#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ENTRY_ESPFIX_SS             (GDT_ENTRY_KERNEL_BASE+14)
+#define __ESPFIX_SS                     (GDT_ENTRY_ESPFIX_SS*8)
 
-#define GDT_ENTRY_PERCPU                        (GDT_ENTRY_KERNEL_BASE + 15)
+#define GDT_ENTRY_PERCPU                (GDT_ENTRY_KERNEL_BASE+15)
 #ifdef CONFIG_SMP
 #define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
 #else
 #define __KERNEL_PERCPU 0
 #endif
 
-#define GDT_ENTRY_STACK_CANARY          (GDT_ENTRY_KERNEL_BASE + 16)
+#define GDT_ENTRY_STACK_CANARY          (GDT_ENTRY_KERNEL_BASE+16)
 #ifdef CONFIG_CC_STACKPROTECTOR
-#define __KERNEL_STACK_CANARY           (GDT_ENTRY_STACK_CANARY * 8)
+#define __KERNEL_STACK_CANARY           (GDT_ENTRY_STACK_CANARY*8)
 #else
 #define __KERNEL_STACK_CANARY           0
 #endif
@@ -182,10 +184,10 @@
 
 #endif
 
-#define __KERNEL_CS     (GDT_ENTRY_KERNEL_CS * 8)
-#define __KERNEL_DS     (GDT_ENTRY_KERNEL_DS * 8)
-#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
-#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
+#define __KERNEL_CS     (GDT_ENTRY_KERNEL_CS*8)
+#define __KERNEL_DS     (GDT_ENTRY_KERNEL_DS*8)
+#define __USER_DS       (GDT_ENTRY_DEFAULT_USER_DS*8+3)
+#define __USER_CS       (GDT_ENTRY_DEFAULT_USER_CS*8+3)
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ef292c792d74..9756551ec760 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
 
 /*
@@ -82,7 +88,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)                                            \
-        static void __section(.discard.text) __used                     \
+        static void __section(.discard.text) __used notrace             \
         __brk_reservation_fn_##name##__(void) {                         \
                 asm volatile (                                          \
                         ".pushsection .brk_reservation,\"aw\",@nobits;" \
@@ -93,10 +99,15 @@ void *extend_brk(size_t size, size_t align);
                         : : "i" (sz));                                  \
         }
 
+/* Helper for reserving space for arrays of things */
+#define RESERVE_BRK_ARRAY(type, name, entries)          \
+        type *name;                                     \
+        RESERVE_BRK(name, sizeof(type) * entries)
+
+extern void probe_roms(void);
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
-extern void probe_roms(void);
 
 #else
 void __init x86_64_start_kernel(char *real_mode);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4cfc90824068..73b11bc0ae6f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -17,12 +17,24 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
+#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
+static inline bool cpu_has_ht_siblings(void)
+{
+        bool has_siblings = false;
+#ifdef CONFIG_SMP
+        has_siblings = cpu_has_ht && smp_num_siblings > 1;
+#endif
+        return has_siblings;
+}
+
 DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+/* cpus sharing the last level cache: */
+DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
@@ -36,21 +48,26 @@ static inline struct cpumask *cpu_core_mask(int cpu)
         return per_cpu(cpu_core_map, cpu);
 }
 
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+        return per_cpu(cpu_llc_shared_map, cpu);
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
+#endif
 
 /* Static state in head.S used to set up a CPU */
-extern struct {
-        void *sp;
-        unsigned short ss;
-} stack_start;
+extern unsigned long stack_start; /* Initial stack pointer address */
 
 struct smp_ops {
         void (*smp_prepare_boot_cpu)(void);
         void (*smp_prepare_cpus)(unsigned max_cpus);
         void (*smp_cpus_done)(unsigned max_cpus);
 
-        void (*smp_send_stop)(void);
+        void (*stop_other_cpus)(int wait);
         void (*smp_send_reschedule)(int cpu);
 
         int (*cpu_up)(unsigned cpu);
@@ -73,7 +90,12 @@ extern struct smp_ops smp_ops;
 
 static inline void smp_send_stop(void)
 {
-        smp_ops.smp_send_stop();
+        smp_ops.stop_other_cpus(0);
+}
+
+static inline void stop_other_cpus(void)
+{
+        smp_ops.stop_other_cpus(1);
 }
 
 static inline void smp_prepare_boot_cpu(void)
diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 1def60114906..725b77831993 100644
--- a/arch/x86/include/asm/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
          */
         CMOS_WRITE(0, 0xf);
 
-        *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0;
+        *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0;
 }
 
 static inline void __init smpboot_setup_io_apic(void)
@@ -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/srat.h b/arch/x86/include/asm/srat.h
deleted file mode 100644
index b508d639d1a7..000000000000
--- a/arch/x86/include/asm/srat.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-
-#ifndef _ASM_X86_SRAT_H
-#define _ASM_X86_SRAT_H
-
-#ifdef CONFIG_ACPI_NUMA
-extern int get_memcfg_from_srat(void);
-#else
-static inline int get_memcfg_from_srat(void)
-{
-        return 0;
-}
-#endif
-
-#endif /* _ASM_X86_SRAT_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 2b16a2ad23dc..70bbe39043a9 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;
 
@@ -36,9 +37,6 @@ print_context_stack_bp(struct thread_info *tinfo,
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
-        void (*warning)(void *data, char *msg);
-        /* msg must contain %s for the symbol */
-        void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
         void (*address)(void *data, unsigned long address, int reliable);
         /* On negative return stop dumping */
         int (*stack)(void *data, char *name);
@@ -57,13 +55,39 @@ 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, unsigned long bp, 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, unsigned long bp, char *log_lvl);
 
 extern unsigned int code_bytes;
 
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index fd921c3a6841..487055c8c1aa 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -9,8 +9,6 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 
-static inline int arch_prepare_suspend(void) { return 0; }
-
 /* image of the saved processor state */
 struct saved_context {
         u16 es, fs, gs, ss;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 8d942afae681..09b0bf104156 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -9,11 +9,6 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 
-static inline int arch_prepare_suspend(void)
-{
-        return 0;
-}
-
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
  * RAM code and by the low level hibernation code.
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 0e831059ac5a..f2b83bc7d784 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -47,14 +47,13 @@ enum {
         INTERCEPT_MONITOR,
         INTERCEPT_MWAIT,
         INTERCEPT_MWAIT_COND,
+        INTERCEPT_XSETBV,
 };
 
 
 struct __attribute__ ((__packed__)) vmcb_control_area {
-        u16 intercept_cr_read;
-        u16 intercept_cr_write;
-        u16 intercept_dr_read;
-        u16 intercept_dr_write;
+        u32 intercept_cr;
+        u32 intercept_dr;
         u32 intercept_exceptions;
         u64 intercept;
         u8 reserved_1[42];
@@ -81,14 +80,19 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
         u32 event_inj_err;
         u64 nested_cr3;
         u64 lbr_ctl;
-        u64 reserved_5;
+        u32 clean;
+        u32 reserved_5;
         u64 next_rip;
-        u8 reserved_6[816];
+        u8 insn_len;
+        u8 insn_bytes[15];
+        u8 reserved_6[800];
 };
 
 
 #define TLB_CONTROL_DO_NOTHING 0
 #define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
 
 #define V_TPR_MASK 0x0f
 
@@ -204,19 +208,31 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
 #define SVM_SELECTOR_CODE_MASK (1 << 3)
 
-#define INTERCEPT_CR0_MASK 1
-#define INTERCEPT_CR3_MASK (1 << 3)
-#define INTERCEPT_CR4_MASK (1 << 4)
-#define INTERCEPT_CR8_MASK (1 << 8)
-
-#define INTERCEPT_DR0_MASK 1
-#define INTERCEPT_DR1_MASK (1 << 1)
-#define INTERCEPT_DR2_MASK (1 << 2)
-#define INTERCEPT_DR3_MASK (1 << 3)
-#define INTERCEPT_DR4_MASK (1 << 4)
-#define INTERCEPT_DR5_MASK (1 << 5)
-#define INTERCEPT_DR6_MASK (1 << 6)
-#define INTERCEPT_DR7_MASK (1 << 7)
+#define INTERCEPT_CR0_READ      0
+#define INTERCEPT_CR3_READ      3
+#define INTERCEPT_CR4_READ      4
+#define INTERCEPT_CR8_READ      8
+#define INTERCEPT_CR0_WRITE     (16 + 0)
+#define INTERCEPT_CR3_WRITE     (16 + 3)
+#define INTERCEPT_CR4_WRITE     (16 + 4)
+#define INTERCEPT_CR8_WRITE     (16 + 8)
+
+#define INTERCEPT_DR0_READ      0
+#define INTERCEPT_DR1_READ      1
+#define INTERCEPT_DR2_READ      2
+#define INTERCEPT_DR3_READ      3
+#define INTERCEPT_DR4_READ      4
+#define INTERCEPT_DR5_READ      5
+#define INTERCEPT_DR6_READ      6
+#define INTERCEPT_DR7_READ      7
+#define INTERCEPT_DR0_WRITE     (16 + 0)
+#define INTERCEPT_DR1_WRITE     (16 + 1)
+#define INTERCEPT_DR2_WRITE     (16 + 2)
+#define INTERCEPT_DR3_WRITE     (16 + 3)
+#define INTERCEPT_DR4_WRITE     (16 + 4)
+#define INTERCEPT_DR5_WRITE     (16 + 5)
+#define INTERCEPT_DR6_WRITE     (16 + 6)
+#define INTERCEPT_DR7_WRITE     (16 + 7)
 
 #define SVM_EVTINJ_VEC_MASK 0xff
 
@@ -246,6 +262,8 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
 #define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
 
+#define SVM_EXITINFO_REG_MASK 0x0F
+
 #define SVM_EXIT_READ_CR0       0x000
 #define SVM_EXIT_READ_CR3       0x003
 #define SVM_EXIT_READ_CR4       0x004
@@ -316,6 +334,7 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EXIT_MONITOR        0x08a
 #define SVM_EXIT_MWAIT          0x08b
 #define SVM_EXIT_MWAIT_COND     0x08c
+#define SVM_EXIT_XSETBV         0x08d
 #define SVM_EXIT_NPF            0x400
 
 #define SVM_EXIT_ERR            -1
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 8085277e1b8b..977f1761a25d 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -5,17 +5,26 @@
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern int __init pci_swiotlb_detect(void);
+extern int __init pci_swiotlb_detect_override(void);
+extern int __init pci_swiotlb_detect_4gb(void);
 extern void __init pci_swiotlb_init(void);
+extern void __init pci_swiotlb_late_init(void);
 #else
 #define swiotlb 0
-static inline int pci_swiotlb_detect(void)
+static inline int pci_swiotlb_detect_override(void)
+{
+        return 0;
+}
+static inline int pci_swiotlb_detect_4gb(void)
 {
         return 0;
 }
 static inline void pci_swiotlb_init(void)
 {
 }
+static inline void pci_swiotlb_late_init(void)
+{
+}
 #endif
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 33ecc3ea8782..c2ff2a1d845e 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -98,8 +98,6 @@ do {									\
  */
 #define HAVE_DISABLE_HLT
 #else
-#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
-#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
 
 /* frame pointer must be last for get_wchan */
 #define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
@@ -305,24 +303,81 @@ static inline void native_wbinvd(void)
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define read_cr0()      (native_read_cr0())
-#define write_cr0(x)    (native_write_cr0(x))
-#define read_cr2()      (native_read_cr2())
-#define write_cr2(x)    (native_write_cr2(x))
-#define read_cr3()      (native_read_cr3())
-#define write_cr3(x)    (native_write_cr3(x))
-#define read_cr4()      (native_read_cr4())
-#define read_cr4_safe() (native_read_cr4_safe())
-#define write_cr4(x)    (native_write_cr4(x))
-#define wbinvd()        (native_wbinvd())
+
+static inline unsigned long read_cr0(void)
+{
+        return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+        native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+        return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+        native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+        return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+        native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+        return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+        return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+        native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+        native_wbinvd();
+}
+
 #ifdef CONFIG_X86_64
-#define read_cr8()      (native_read_cr8())
-#define write_cr8(x)    (native_write_cr8(x))
-#define load_gs_index   native_load_gs_index
+
+static inline unsigned long read_cr8(void)
+{
+        return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+        native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+        native_load_gs_index(selector);
+}
+
 #endif
 
 /* Clear the 'TS' bit */
-#define clts()          (native_clts())
+static inline void clts(void)
+{
+        native_clts();
+}
 
 #endif/* CONFIG_PARAVIRT */
 
diff --git a/arch/x86/include/asm/system_64.h b/arch/x86/include/asm/system_64.h
deleted file mode 100644
index 1159e091ad09..000000000000
--- a/arch/x86/include/asm/system_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_64_H
-#define _ASM_X86_SYSTEM_64_H
-
-#include <asm/segment.h>
-#include <asm/cmpxchg.h>
-
-
-static inline unsigned long read_cr8(void)
-{
-        unsigned long cr8;
-        asm volatile("movq %%cr8,%0" : "=r" (cr8));
-        return cr8;
-}
-
-static inline void write_cr8(unsigned long val)
-{
-        asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-
-#include <linux/irqflags.h>
-
-#endif /* _ASM_X86_SYSTEM_64_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f0b6e5dbc5a0..1f2e61e28981 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -161,8 +161,14 @@ struct thread_info {
 
 #define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
 
-#define alloc_thread_info(tsk)                                          \
-        ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+#define alloc_thread_info_node(tsk, node)                               \
+({                                                                      \
+        struct page *page = alloc_pages_node(node, THREAD_FLAGS,        \
+                                             THREAD_ORDER);             \
+        struct thread_info *ret = page ? page_address(page) : NULL;     \
+                                                                        \
+        ret;                                                            \
+})
 
 #ifdef CONFIG_X86_32
 
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/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 7f3eba08e7de..169be8938b96 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -172,6 +172,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
         flush_tlb_all();
 }
 
-extern void zap_low_mappings(bool early);
-
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 21899cc31e52..c00692476e9f 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -47,21 +47,6 @@
 
 #include <asm/mpspec.h>
 
-#ifdef CONFIG_X86_32
-
-/* Mappings between logical cpu number and node number */
-extern int cpu_to_node_map[];
-
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int __cpu_to_node(int cpu)
-{
-        return cpu_to_node_map[cpu];
-}
-#define early_cpu_to_node __cpu_to_node
-#define cpu_to_node __cpu_to_node
-
-#else /* CONFIG_X86_64 */
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -84,8 +69,6 @@ static inline int early_cpu_to_node(int cpu)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-#endif /* CONFIG_X86_64 */
-
 /* Mappings between node number and cpus on that node. */
 extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 
@@ -110,19 +93,11 @@ extern void setup_node_to_cpumask_map(void);
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
 #ifdef CONFIG_X86_32
-extern unsigned long node_start_pfn[];
-extern unsigned long node_end_pfn[];
-extern unsigned long node_remap_size[];
-#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
-
 # define SD_CACHE_NICE_TRIES    1
 # define SD_IDLE_IDX            1
-
 #else
-
 # define SD_CACHE_NICE_TRIES    2
 # define SD_IDLE_IDX            2
-
 #endif
 
 /* sched_domains SD_NODE_INIT for NUMA machines */
@@ -155,7 +130,7 @@ extern unsigned long node_remap_size[];
         .balance_interval       = 1,                                    \
 }
 
-#ifdef CONFIG_X86_64_ACPI_NUMA
+#ifdef CONFIG_X86_64
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 #endif
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 4dde797c0578..feca3118a73b 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -3,28 +3,36 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_X86_TRAMPOLINE
+#include <linux/types.h>
+#include <asm/io.h>
+
 /*
- * Trampoline 80x86 program as an array.
+ * Trampoline 80x86 program as an array.  These are in the init rodata
+ * segment, but that's okay, because we only care about the relative
+ * addresses of the symbols.
  */
-extern const unsigned char trampoline_data [];
-extern const unsigned char trampoline_end  [];
-extern unsigned char *trampoline_base;
+extern const unsigned char x86_trampoline_start [];
+extern const unsigned char x86_trampoline_end   [];
+extern unsigned char *x86_trampoline_base;
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
-extern unsigned long initial_page_table;
 extern unsigned long initial_gs;
 
-#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
+extern void __init setup_trampolines(void);
+
+extern const unsigned char trampoline_data[];
+extern const unsigned char trampoline_status[];
+
+#define TRAMPOLINE_SYM(x)                                               \
+        ((void *)(x86_trampoline_base +                                 \
+                  ((const unsigned char *)(x) - x86_trampoline_start)))
 
-extern unsigned long setup_trampoline(void);
-extern void __init setup_trampoline_page_table(void);
-extern void __init reserve_trampoline_memory(void);
-#else
-static inline void setup_trampoline_page_table(void) {}
-static inline void reserve_trampoline_memory(void) {}
-#endif /* CONFIG_X86_TRAMPOLINE */
+/* Address of the SMP trampoline */
+static inline unsigned long trampoline_address(void)
+{
+        return virt_to_phys(TRAMPOLINE_SYM(trampoline_data));
+}
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index f66cda56781d..0310da67307f 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -30,6 +30,7 @@ asmlinkage void segment_not_present(void);
 asmlinkage void stack_segment(void);
 asmlinkage void general_protection(void);
 asmlinkage void page_fault(void);
+asmlinkage void async_page_fault(void);
 asmlinkage void spurious_interrupt_bug(void);
 asmlinkage void coprocessor_error(void);
 asmlinkage void alignment_check(void);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 1ca132fc0d03..9db5583b6d38 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -35,7 +35,7 @@ static inline cycles_t get_cycles(void)
 static __always_inline cycles_t vget_cycles(void)
 {
         /*
-         * We only do VDSOs on TSC capable CPUs, so this shouldnt
+         * We only do VDSOs on TSC capable CPUs, so this shouldn't
          * access boot_cpu_data (which is not VDSO-safe):
          */
 #ifndef CONFIG_X86_TSC
@@ -51,6 +51,10 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern unsigned long native_calibrate_tsc(void);
 
+#ifdef CONFIG_X86_64
+extern cycles_t vread_tsc(void);
+#endif
+
 /*
  * Boot-time check whether the TSCs are synchronized across
  * all CPUs/cores:
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
index df1da20f4534..8e8c23fef08c 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -1,22 +1,6 @@
 #ifndef _ASM_X86_TYPES_H
 #define _ASM_X86_TYPES_H
 
-#define dma_addr_t      dma_addr_t
-
 #include <asm-generic/types.h>
 
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-typedef u64 dma64_addr_t;
-#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G)
-/* DMA addresses come in 32-bit and 64-bit flavours. */
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
 #endif /* _ASM_X86_TYPES_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index abd3e0ea762a..99ddd148a760 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -6,7 +6,6 @@
 #include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/thread_info.h>
-#include <linux/prefetch.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
@@ -42,7 +41,7 @@
  * Returns 0 if the range is valid, nonzero otherwise.
  *
  * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
  *
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 088d09fb1615..566e803cc602 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -6,7 +6,6 @@
  */
 #include <linux/errno.h>
 #include <linux/thread_info.h>
-#include <linux/prefetch.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 316708d5af92..1c66d30971ad 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -6,7 +6,6 @@
  */
 #include <linux/compiler.h>
 #include <linux/errno.h>
-#include <linux/prefetch.h>
 #include <linux/lockdep.h>
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index b7ba19acd3f8..2f6e127db30c 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -346,14 +346,20 @@
 #define __NR_fanotify_init      338
 #define __NR_fanotify_mark      339
 #define __NR_prlimit64          340
+#define __NR_name_to_handle_at  341
+#define __NR_open_by_handle_at  342
+#define __NR_clock_adjtime      343
+#define __NR_syncfs             344
+#define __NR_sendmmsg           345
+#define __NR_setns              346
 
-#define __NR_LITMUS             341
+#define __NR_LITMUS             347
 
 #include "litmus/unistd_32.h"
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 341 + NR_litmus_syscalls
+#define NR_syscalls 347 + NR_litmus_syscalls
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 332bf3c9c84c..e347f0773788 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -669,8 +669,20 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
 #define __NR_prlimit64                          302
 __SYSCALL(__NR_prlimit64, sys_prlimit64)
-
-#define __NR_LITMUS                             303
+#define __NR_name_to_handle_at                  303
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at                  304
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#define __NR_clock_adjtime                      305
+__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
+#define __NR_syncfs                             306
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_sendmmsg                           307
+__SYSCALL(__NR_sendmmsg, sys_sendmmsg)
+#define __NR_setns                              308
+__SYSCALL(__NR_setns, sys_setns)
+
+#define __NR_LITMUS                             309
 
 #include "litmus/unistd_64.h"
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 42d412fd8b02..a291c40efd43 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -5,7 +5,7 @@
  *
  * SGI UV Broadcast Assist Unit definitions
  *
- * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2008-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_BAU_H
@@ -26,24 +26,29 @@
  * 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 UV_ITEMS_PER_DESCRIPTOR         8
+#define MAX_CPUS_PER_UVHUB              64
+#define MAX_CPUS_PER_SOCKET             32
+#define ADP_SZ                          64 /* hardware-provided max. */
+#define UV_CPUS_PER_AS                  32 /* hardware-provided max. */
+#define ITEMS_PER_DESC                  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
-#define UV_DESC_BASE_PNODE_SHIFT        49
+#define UV1_NET_ENDPOINT_INTD           0x38
+#define UV2_NET_ENDPOINT_INTD           0x28
+#define UV_NET_ENDPOINT_INTD            (is_uv1_hub() ?                 \
+                        UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
+#define UV_DESC_PSHIFT                  49
 #define UV_PAYLOADQ_PNODE_SHIFT         49
 #define UV_PTC_BASENAME                 "sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME                 "sgi_uv/bau_tunables"
@@ -51,29 +56,64 @@
 #define UV_BAU_TUNABLES_FILE            "bau_tunables"
 #define WHITESPACE                      " \t\n"
 #define uv_physnodeaddr(x)              ((__pa((unsigned long)(x)) & uv_mmask))
-#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL
+#define cpubit_isset(cpu, bau_local_cpumask) \
+        test_bit((cpu), (bau_local_cpumask).bits)
+
 /* [19:16] SOFT_ACK timeout period  19: 1 is urgency 7  17:16 1 is multiplier */
-#define BAU_MISC_CONTROL_MULT_MASK 3
+/*
+ * UV2: Bit 19 selects between
+ *  (0): 10 microsecond timebase and
+ *  (1): 80 microseconds
+ *  we're using 655us, similar to UV1: 65 units of 10us
+ */
+#define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
+#define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (65*10UL)
+
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD (is_uv1_hub() ?                 \
+                UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD :                      \
+                UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD)
 
-#define UVH_AGING_PRESCALE_SEL 0x000000b000UL
+#define BAU_MISC_CONTROL_MULT_MASK      3
+
+#define UVH_AGING_PRESCALE_SEL          0x000000b000UL
 /* [30:28] URGENCY_7  an index into a table of times */
-#define BAU_URGENCY_7_SHIFT 28
-#define BAU_URGENCY_7_MASK 7
+#define BAU_URGENCY_7_SHIFT             28
+#define BAU_URGENCY_7_MASK              7
 
-#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL
+#define UVH_TRANSACTION_TIMEOUT         0x000000b200UL
 /* [45:40] BAU - BAU transaction timeout select - a multiplier */
-#define BAU_TRANS_SHIFT 40
-#define BAU_TRANS_MASK 0x3f
+#define BAU_TRANS_SHIFT                 40
+#define BAU_TRANS_MASK                  0x3f
+
+/*
+ * shorten some awkward names
+ */
+#define AS_PUSH_SHIFT UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT
+#define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT
+#define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD
+#define write_gmmr      uv_write_global_mmr64
+#define write_lmmr      uv_write_local_mmr
+#define read_lmmr       uv_read_local_mmr
+#define read_gmmr       uv_read_global_mmr64
 
 /*
  * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
  */
-#define DESC_STATUS_IDLE                0
-#define DESC_STATUS_ACTIVE              1
-#define DESC_STATUS_DESTINATION_TIMEOUT 2
-#define DESC_STATUS_SOURCE_TIMEOUT      3
+#define DS_IDLE                         0
+#define DS_ACTIVE                       1
+#define DS_DESTINATION_TIMEOUT          2
+#define DS_SOURCE_TIMEOUT               3
+/*
+ * bits put together from HRP_LB_BAU_SB_ACTIVATION_STATUS_0/1/2
+ * values 1 and 5 will not occur
+ */
+#define UV2H_DESC_IDLE                  0
+#define UV2H_DESC_DEST_TIMEOUT          2
+#define UV2H_DESC_DEST_STRONG_NACK      3
+#define UV2H_DESC_BUSY                  4
+#define UV2H_DESC_SOURCE_TIMEOUT        6
+#define UV2H_DESC_DEST_PUT_ERR          7
 
 /*
  * delay for 'plugged' timeout retries, in microseconds
@@ -84,13 +124,24 @@
  * threshholds at which to use IPI to free resources
  */
 /* after this # consecutive 'plugged' timeouts, use IPI to release resources */
-#define PLUGSB4RESET 100
+#define PLUGSB4RESET                    100
 /* after this many consecutive timeouts, use IPI to release resources */
-#define TIMEOUTSB4RESET 1
+#define TIMEOUTSB4RESET                 1
 /* at this number uses of IPI to release resources, giveup the request */
-#define IPI_RESET_LIMIT 1
+#define IPI_RESET_LIMIT                 1
 /* after this # consecutive successes, bump up the throttle if it was lowered */
-#define COMPLETE_THRESHOLD 5
+#define COMPLETE_THRESHOLD              5
+
+#define UV_LB_SUBNODEID                 0x10
+
+/* these two are the same for UV1 and UV2: */
+#define UV_SA_SHFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define UV_SA_MASK UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK
+/* 4 bits of software ack period */
+#define UV2_ACK_MASK                    0x7UL
+#define UV2_ACK_UNITS_SHFT              3
+#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
+#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 
 /*
  * number of entries in the destination side payload queue
@@ -100,7 +151,6 @@
  * 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
  */
@@ -112,9 +162,16 @@
 /*
  * tuning the action when the numalink network is extremely delayed
  */
-#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */
-#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */
-#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */
+#define CONGESTED_RESPONSE_US           1000    /* 'long' response time, in
+                                                   microseconds */
+#define CONGESTED_REPS                  10      /* long delays averaged over
+                                                   this many broadcasts */
+#define CONGESTED_PERIOD                30      /* time for the bau to be
+                                                   disabled, in seconds */
+/* see msg_type: */
+#define MSG_NOOP                        0
+#define MSG_REGULAR                     1
+#define MSG_RETRY                       2
 
 /*
  * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
@@ -123,11 +180,11 @@
  * The distribution specification (32 bytes) is interpreted as a 256-bit
  * distribution vector. Adjacent bits correspond to consecutive even numbered
  * nodeIDs. The result of adding the index of a given bit to the 15-bit
- * 'base_dest_nodeid' field of the header corresponds to the
+ * 'base_dest_nasid' field of the header corresponds to the
  * destination nodeID associated with that specified bit.
  */
-struct bau_target_uvhubmask {
-        unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
+struct bau_targ_hubmask {
+        unsigned long           bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
 };
 
 /*
@@ -136,7 +193,7 @@ struct bau_target_uvhubmask {
  *  enough bits for max. cpu's per uvhub)
  */
 struct bau_local_cpumask {
-        unsigned long bits;
+        unsigned long           bits;
 };
 
 /*
@@ -157,14 +214,14 @@ struct bau_local_cpumask {
  * The payload is software-defined for INTD transactions
  */
 struct bau_msg_payload {
-        unsigned long address;          /* signifies a page or all TLB's
-                                                of the cpu */
+        unsigned long   address;                /* signifies a page or all
+                                                   TLB's of the cpu */
         /* 64 bits */
-        unsigned short sending_cpu;     /* filled in by sender */
+        unsigned short  sending_cpu;            /* filled in by sender */
         /* 16 bits */
-        unsigned short acknowledge_count;/* filled in by destination */
+        unsigned short  acknowledge_count;      /* filled in by destination */
         /* 16 bits */
-        unsigned int reserved1:32;      /* not usable */
+        unsigned int    reserved1:32;           /* not usable */
 };
 
 
@@ -173,93 +230,96 @@ struct bau_msg_payload {
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
 struct bau_msg_header {
-        unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
+        unsigned int    dest_subnodeid:6;       /* must be 0x10, for the LB */
         /* bits 5:0 */
-        unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */
-        /* bits 20:6 */                   /* first bit in uvhub map */
-        unsigned int command:8; /* message type */
+        unsigned int    base_dest_nasid:15;     /* nasid of the first bit */
+        /* bits 20:6 */                         /* in uvhub map */
+        unsigned int    command:8;              /* message type */
         /* bits 28:21 */
-                                /* 0x38: SN3net EndPoint Message */
-        unsigned int rsvd_1:3;  /* must be zero */
+        /* 0x38: SN3net EndPoint Message */
+        unsigned int    rsvd_1:3;               /* must be zero */
         /* bits 31:29 */
-                                /* int will align on 32 bits */
-        unsigned int rsvd_2:9;  /* must be zero */
+        /* int will align on 32 bits */
+        unsigned int    rsvd_2:9;               /* must be zero */
         /* bits 40:32 */
-                                /* Suppl_A is 56-41 */
-        unsigned int sequence:16;/* message sequence number */
-        /* bits 56:41 */        /* becomes bytes 16-17 of msg */
-                                /* Address field (96:57) is never used as an
-                                   address (these are address bits 42:3) */
-
-        unsigned int rsvd_3:1;  /* must be zero */
+        /* Suppl_A is 56-41 */
+        unsigned int    sequence:16;            /* message sequence number */
+        /* bits 56:41 */                        /* becomes bytes 16-17 of msg */
+                                                /* Address field (96:57) is
+                                                   never used as an address
+                                                   (these are address bits
+                                                   42:3) */
+
+        unsigned int    rsvd_3:1;               /* must be zero */
         /* bit 57 */
-                                /* address bits 27:4 are payload */
+        /* address bits 27:4 are payload */
         /* these next 24  (58-81) bits become bytes 12-14 of msg */
-
         /* bits 65:58 land in byte 12 */
-        unsigned int replied_to:1;/* sent as 0 by the source to byte 12 */
+        unsigned int    replied_to:1;           /* sent as 0 by the source to
+                                                   byte 12 */
         /* bit 58 */
-        unsigned int msg_type:3; /* software type of the message*/
+        unsigned int    msg_type:3;             /* software type of the
+                                                   message */
         /* bits 61:59 */
-        unsigned int canceled:1; /* message canceled, resource to be freed*/
+        unsigned int    canceled:1;             /* message canceled, resource
+                                                   is to be freed*/
         /* bit 62 */
-        unsigned int payload_1a:1;/* not currently used */
+        unsigned int    payload_1a:1;           /* not currently used */
         /* bit 63 */
-        unsigned int payload_1b:2;/* not currently used */
+        unsigned int    payload_1b:2;           /* not currently used */
         /* bits 65:64 */
 
         /* bits 73:66 land in byte 13 */
-        unsigned int payload_1ca:6;/* not currently used */
+        unsigned int    payload_1ca:6;          /* not currently used */
         /* bits 71:66 */
-        unsigned int payload_1c:2;/* not currently used */
+        unsigned int    payload_1c:2;           /* not currently used */
         /* bits 73:72 */
 
         /* bits 81:74 land in byte 14 */
-        unsigned int payload_1d:6;/* not currently used */
+        unsigned int    payload_1d:6;           /* not currently used */
         /* bits 79:74 */
-        unsigned int payload_1e:2;/* not currently used */
+        unsigned int    payload_1e:2;           /* not currently used */
         /* bits 81:80 */
 
-        unsigned int rsvd_4:7;  /* must be zero */
+        unsigned int    rsvd_4:7;               /* must be zero */
         /* bits 88:82 */
-        unsigned int sw_ack_flag:1;/* software acknowledge flag */
+        unsigned int    swack_flag:1;           /* software acknowledge flag */
         /* bit 89 */
-                                /* INTD trasactions at destination are to
-                                   wait for software acknowledge */
-        unsigned int rsvd_5:6;  /* must be zero */
+                                                /* INTD trasactions at
+                                                   destination are to wait for
+                                                   software acknowledge */
+        unsigned int    rsvd_5:6;               /* must be zero */
         /* bits 95:90 */
-        unsigned int rsvd_6:5;  /* must be zero */
+        unsigned int    rsvd_6:5;               /* must be zero */
         /* bits 100:96 */
-        unsigned int int_both:1;/* if 1, interrupt both sockets on the uvhub */
+        unsigned int    int_both:1;             /* if 1, interrupt both sockets
+                                                   on the uvhub */
         /* bit 101*/
-        unsigned int fairness:3;/* usually zero */
+        unsigned int    fairness:3;             /* usually zero */
         /* bits 104:102 */
-        unsigned int multilevel:1;      /* multi-level multicast format */
+        unsigned int    multilevel:1;           /* multi-level multicast
+                                                   format */
         /* bit 105 */
-                                /* 0 for TLB: endpoint multi-unicast messages */
-        unsigned int chaining:1;/* next descriptor is part of this activation*/
+        /* 0 for TLB: endpoint multi-unicast messages */
+        unsigned int    chaining:1;             /* next descriptor is part of
+                                                   this activation*/
         /* bit 106 */
-        unsigned int rsvd_7:21; /* must be zero */
+        unsigned int    rsvd_7:21;              /* must be zero */
         /* bits 127:107 */
 };
 
-/* see msg_type: */
-#define MSG_NOOP 0
-#define MSG_REGULAR 1
-#define MSG_RETRY 2
-
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-        struct bau_target_uvhubmask distribution;
+        struct bau_targ_hubmask distribution;
         /*
          * message template, consisting of header and payload:
          */
-        struct bau_msg_header header;
-        struct bau_msg_payload payload;
+        struct bau_msg_header           header;
+        struct bau_msg_payload          payload;
 };
 /*
  *   -payload--    ---------header------
@@ -278,59 +338,51 @@ struct bau_desc {
  * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
  * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
  * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
- *  sw_ack_vector and payload_2)
+ *  swack_vec and payload_2)
  * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
  *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
  *  operation."
  */
-struct bau_payload_queue_entry {
-        unsigned long address;          /* signifies a page or all TLB's
-                                                of the cpu */
+struct bau_pq_entry {
+        unsigned long   address;        /* signifies a page or all TLB's
+                                           of the cpu */
         /* 64 bits, bytes 0-7 */
-
-        unsigned short sending_cpu;     /* cpu that sent the message */
+        unsigned short  sending_cpu;    /* cpu that sent the message */
         /* 16 bits, bytes 8-9 */
-
-        unsigned short acknowledge_count; /* filled in by destination */
+        unsigned short  acknowledge_count; /* filled in by destination */
         /* 16 bits, bytes 10-11 */
-
         /* these next 3 bytes come from bits 58-81 of the message header */
-        unsigned short replied_to:1;    /* sent as 0 by the source */
-        unsigned short msg_type:3;      /* software message type */
-        unsigned short canceled:1;      /* sent as 0 by the source */
-        unsigned short unused1:3;       /* not currently using */
+        unsigned short  replied_to:1;   /* sent as 0 by the source */
+        unsigned short  msg_type:3;     /* software message type */
+        unsigned short  canceled:1;     /* sent as 0 by the source */
+        unsigned short  unused1:3;      /* not currently using */
         /* byte 12 */
-
-        unsigned char unused2a;         /* not currently using */
+        unsigned char   unused2a;       /* not currently using */
         /* byte 13 */
-        unsigned char unused2;          /* not currently using */
+        unsigned char   unused2;        /* not currently using */
         /* byte 14 */
-
-        unsigned char sw_ack_vector;    /* filled in by the hardware */
+        unsigned char   swack_vec;      /* filled in by the hardware */
         /* byte 15 (bits 127:120) */
-
-        unsigned short sequence;        /* message sequence number */
+        unsigned short  sequence;       /* message sequence number */
         /* bytes 16-17 */
-        unsigned char unused4[2];       /* not currently using bytes 18-19 */
+        unsigned char   unused4[2];     /* not currently using bytes 18-19 */
         /* bytes 18-19 */
-
-        int number_of_cpus;             /* filled in at destination */
+        int             number_of_cpus; /* filled in at destination */
         /* 32 bits, bytes 20-23 (aligned) */
-
-        unsigned char unused5[8];       /* not using */
+        unsigned char   unused5[8];     /* not using */
         /* bytes 24-31 */
 };
 
 struct msg_desc {
-        struct bau_payload_queue_entry *msg;
-        int msg_slot;
-        int sw_ack_slot;
-        struct bau_payload_queue_entry *va_queue_first;
-        struct bau_payload_queue_entry *va_queue_last;
+        struct bau_pq_entry     *msg;
+        int                     msg_slot;
+        int                     swack_slot;
+        struct bau_pq_entry     *queue_first;
+        struct bau_pq_entry     *queue_last;
 };
 
 struct reset_args {
-        int sender;
+        int                     sender;
 };
 
 /*
@@ -338,105 +390,226 @@ struct reset_args {
  */
 struct ptc_stats {
         /* sender statistics */
-        unsigned long s_giveup; /* number of fall backs to IPI-style flushes */
-        unsigned long s_requestor; /* number of shootdown requests */
-        unsigned long s_stimeout; /* source side timeouts */
-        unsigned long s_dtimeout; /* destination side timeouts */
-        unsigned long s_time; /* time spent in sending side */
-        unsigned long s_retriesok; /* successful retries */
-        unsigned long s_ntargcpu; /* total number of cpu's targeted */
-        unsigned long s_ntargself; /* times the sending cpu was targeted */
-        unsigned long s_ntarglocals; /* targets of cpus on the local blade */
-        unsigned long s_ntargremotes; /* targets of cpus on remote blades */
-        unsigned long s_ntarglocaluvhub; /* targets of the local hub */
-        unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */
-        unsigned long s_ntarguvhub; /* total number of uvhubs targeted */
-        unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/
-        unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */
-        unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */
-        unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */
-        unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */
-        unsigned long s_resets_plug; /* ipi-style resets from plug state */
-        unsigned long s_resets_timeout; /* ipi-style resets from timeouts */
-        unsigned long s_busy; /* status stayed busy past s/w timer */
-        unsigned long s_throttles; /* waits in throttle */
-        unsigned long s_retry_messages; /* retry broadcasts */
-        unsigned long s_bau_reenabled; /* for bau enable/disable */
-        unsigned long s_bau_disabled; /* for bau enable/disable */
+        unsigned long   s_giveup;               /* number of fall backs to
+                                                   IPI-style flushes */
+        unsigned long   s_requestor;            /* number of shootdown
+                                                   requests */
+        unsigned long   s_stimeout;             /* source side timeouts */
+        unsigned long   s_dtimeout;             /* destination side timeouts */
+        unsigned long   s_time;                 /* time spent in sending side */
+        unsigned long   s_retriesok;            /* successful retries */
+        unsigned long   s_ntargcpu;             /* total number of cpu's
+                                                   targeted */
+        unsigned long   s_ntargself;            /* times the sending cpu was
+                                                   targeted */
+        unsigned long   s_ntarglocals;          /* targets of cpus on the local
+                                                   blade */
+        unsigned long   s_ntargremotes;         /* targets of cpus on remote
+                                                   blades */
+        unsigned long   s_ntarglocaluvhub;      /* targets of the local hub */
+        unsigned long   s_ntargremoteuvhub;     /* remotes hubs targeted */
+        unsigned long   s_ntarguvhub;           /* total number of uvhubs
+                                                   targeted */
+        unsigned long   s_ntarguvhub16;         /* number of times target
+                                                   hubs >= 16*/
+        unsigned long   s_ntarguvhub8;          /* number of times target
+                                                   hubs >= 8 */
+        unsigned long   s_ntarguvhub4;          /* number of times target
+                                                   hubs >= 4 */
+        unsigned long   s_ntarguvhub2;          /* number of times target
+                                                   hubs >= 2 */
+        unsigned long   s_ntarguvhub1;          /* number of times target
+                                                   hubs == 1 */
+        unsigned long   s_resets_plug;          /* ipi-style resets from plug
+                                                   state */
+        unsigned long   s_resets_timeout;       /* ipi-style resets from
+                                                   timeouts */
+        unsigned long   s_busy;                 /* status stayed busy past
+                                                   s/w timer */
+        unsigned long   s_throttles;            /* waits in throttle */
+        unsigned long   s_retry_messages;       /* retry broadcasts */
+        unsigned long   s_bau_reenabled;        /* for bau enable/disable */
+        unsigned long   s_bau_disabled;         /* for bau enable/disable */
         /* destination statistics */
-        unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */
-        unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */
-        unsigned long d_multmsg; /* interrupts with multiple messages */
-        unsigned long d_nomsg; /* interrupts with no message */
-        unsigned long d_time; /* time spent on destination side */
-        unsigned long d_requestee; /* number of messages processed */
-        unsigned long d_retries; /* number of retry messages processed */
-        unsigned long d_canceled; /* number of messages canceled by retries */
-        unsigned long d_nocanceled; /* retries that found nothing to cancel */
-        unsigned long d_resets; /* number of ipi-style requests processed */
-        unsigned long d_rcanceled; /* number of messages canceled by resets */
+        unsigned long   d_alltlb;               /* times all tlb's on this
+                                                   cpu were flushed */
+        unsigned long   d_onetlb;               /* times just one tlb on this
+                                                   cpu was flushed */
+        unsigned long   d_multmsg;              /* interrupts with multiple
+                                                   messages */
+        unsigned long   d_nomsg;                /* interrupts with no message */
+        unsigned long   d_time;                 /* time spent on destination
+                                                   side */
+        unsigned long   d_requestee;            /* number of messages
+                                                   processed */
+        unsigned long   d_retries;              /* number of retry messages
+                                                   processed */
+        unsigned long   d_canceled;             /* number of messages canceled
+                                                   by retries */
+        unsigned long   d_nocanceled;           /* retries that found nothing
+                                                   to cancel */
+        unsigned long   d_resets;               /* number of ipi-style requests
+                                                   processed */
+        unsigned long   d_rcanceled;            /* number of messages canceled
+                                                   by resets */
+};
+
+struct tunables {
+        int                     *tunp;
+        int                     deflt;
+};
+
+struct hub_and_pnode {
+        short                   uvhub;
+        short                   pnode;
+};
+
+struct socket_desc {
+        short                   num_cpus;
+        short                   cpu_number[MAX_CPUS_PER_SOCKET];
+};
+
+struct uvhub_desc {
+        unsigned short          socket_mask;
+        short                   num_cpus;
+        short                   uvhub;
+        short                   pnode;
+        struct socket_desc      socket[2];
 };
 
 /*
  * one per-cpu; to locate the software tables
  */
 struct bau_control {
-        struct bau_desc *descriptor_base;
-        struct bau_payload_queue_entry *va_queue_first;
-        struct bau_payload_queue_entry *va_queue_last;
-        struct bau_payload_queue_entry *bau_msg_head;
-        struct bau_control *uvhub_master;
-        struct bau_control *socket_master;
-        struct ptc_stats *statp;
-        unsigned long timeout_interval;
-        unsigned long set_bau_on_time;
-        atomic_t active_descriptor_count;
-        int plugged_tries;
-        int timeout_tries;
-        int ipi_attempts;
-        int conseccompletes;
-        int baudisabled;
-        int set_bau_off;
-        short cpu;
-        short uvhub_cpu;
-        short uvhub;
-        short cpus_in_socket;
-        short cpus_in_uvhub;
-        unsigned short message_number;
-        unsigned short uvhub_quiesce;
-        short socket_acknowledge_count[DEST_Q_SIZE];
-        cycles_t send_message;
-        spinlock_t uvhub_lock;
-        spinlock_t queue_lock;
+        struct bau_desc         *descriptor_base;
+        struct bau_pq_entry     *queue_first;
+        struct bau_pq_entry     *queue_last;
+        struct bau_pq_entry     *bau_msg_head;
+        struct bau_control      *uvhub_master;
+        struct bau_control      *socket_master;
+        struct ptc_stats        *statp;
+        unsigned long           timeout_interval;
+        unsigned long           set_bau_on_time;
+        atomic_t                active_descriptor_count;
+        int                     plugged_tries;
+        int                     timeout_tries;
+        int                     ipi_attempts;
+        int                     conseccompletes;
+        int                     baudisabled;
+        int                     set_bau_off;
+        short                   cpu;
+        short                   osnode;
+        short                   uvhub_cpu;
+        short                   uvhub;
+        short                   cpus_in_socket;
+        short                   cpus_in_uvhub;
+        short                   partition_base_pnode;
+        unsigned short          message_number;
+        unsigned short          uvhub_quiesce;
+        short                   socket_acknowledge_count[DEST_Q_SIZE];
+        cycles_t                send_message;
+        spinlock_t              uvhub_lock;
+        spinlock_t              queue_lock;
         /* tunables */
-        int max_bau_concurrent;
-        int max_bau_concurrent_constant;
-        int plugged_delay;
-        int plugsb4reset;
-        int timeoutsb4reset;
-        int ipi_reset_limit;
-        int complete_threshold;
-        int congested_response_us;
-        int congested_reps;
-        int congested_period;
-        cycles_t period_time;
-        long period_requests;
+        int                     max_concurr;
+        int                     max_concurr_const;
+        int                     plugged_delay;
+        int                     plugsb4reset;
+        int                     timeoutsb4reset;
+        int                     ipi_reset_limit;
+        int                     complete_threshold;
+        int                     cong_response_us;
+        int                     cong_reps;
+        int                     cong_period;
+        cycles_t                period_time;
+        long                    period_requests;
+        struct hub_and_pnode    *thp;
 };
 
-static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
+static unsigned long read_mmr_uv2_status(void)
+{
+        return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2);
+}
+
+static void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
+}
+
+static void write_mmr_descriptor_base(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, mmr_image);
+}
+
+static void write_mmr_activation(unsigned long index)
+{
+        write_lmmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index);
+}
+
+static void write_gmmr_activation(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image);
+}
+
+static void write_mmr_payload_first(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image);
+}
+
+static void write_mmr_payload_tail(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, mmr_image);
+}
+
+static void write_mmr_payload_last(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, mmr_image);
+}
+
+static void write_mmr_misc_control(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+}
+
+static unsigned long read_mmr_misc_control(int pnode)
+{
+        return read_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL);
+}
+
+static void write_mmr_sw_ack(unsigned long mr)
+{
+        uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
+static unsigned long read_mmr_sw_ack(void)
+{
+        return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static unsigned long read_gmmr_sw_ack(int pnode)
+{
+        return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static void write_mmr_data_config(int pnode, unsigned long mr)
+{
+        uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr);
+}
+
+static inline int bau_uvhub_isset(int uvhub, struct bau_targ_hubmask *dstp)
 {
         return constant_test_bit(uvhub, &dstp->bits[0]);
 }
-static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_targ_hubmask *dstp)
 {
-        __set_bit(uvhub, &dstp->bits[0]);
+        __set_bit(pnode, &dstp->bits[0]);
 }
-static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
+static inline void bau_uvhubs_clear(struct bau_targ_hubmask *dstp,
                                     int nbits)
 {
         bitmap_zero(&dstp->bits[0], nbits);
 }
-static inline int bau_uvhub_weight(struct bau_target_uvhubmask *dstp)
+static inline int bau_uvhub_weight(struct bau_targ_hubmask *dstp)
 {
         return bitmap_weight((unsigned long *)&dstp->bits[0],
                                 UV_DISTRIBUTION_SIZE);
@@ -447,9 +620,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
         bitmap_zero(&dstp->bits, nbits);
 }
 
-#define cpubit_isset(cpu, bau_local_cpumask) \
-        test_bit((cpu), (bau_local_cpumask).bits)
-
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
@@ -457,7 +627,7 @@ struct atomic_short {
         short counter;
 };
 
-/**
+/*
  * atomic_read_short - read a short atomic variable
  * @v: pointer of type atomic_short
  *
@@ -468,14 +638,14 @@ static inline int atomic_read_short(const struct atomic_short *v)
         return v->counter;
 }
 
-/**
- * atomic_add_short_return - add and return a short int
+/*
+ * atom_asr - add and return a short int
  * @i: short value to add
  * @v: pointer of type atomic_short
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_short_return(short i, struct atomic_short *v)
+static inline int atom_asr(short i, struct atomic_short *v)
 {
         short __i = i;
         asm volatile(LOCK_PREFIX "xaddw %0, %1"
@@ -484,4 +654,26 @@ static inline int atomic_add_short_return(short i, struct atomic_short *v)
         return i + __i;
 }
 
+/*
+ * conditionally add 1 to *v, unless *v is >= u
+ * return 0 if we cannot add 1 to *v because it is >= u
+ * return 1 if we can add 1 to *v because it is < u
+ * the add is atomic
+ *
+ * This is close to atomic_add_unless(), but this allows the 'u' value
+ * to be lowered below the current 'v'.  atomic_add_unless can only stop
+ * on equal.
+ */
+static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+{
+        spin_lock(lock);
+        if (atomic_read(v) >= u) {
+                spin_unlock(lock);
+                return 0;
+        }
+        atomic_inc(v);
+        spin_unlock(lock);
+        return 1;
+}
+
 #endif /* _ASM_X86_UV_UV_BAU_H */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index bf6b88ef8eeb..f26544a15214 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -5,7 +5,7 @@
  *
  * SGI UV architectural definitions
  *
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_HUB_H
@@ -77,7 +77,9 @@
  *
  *              1111110000000000
  *              5432109876543210
- *              pppppppppplc0cch
+ *              pppppppppplc0cch        Nehalem-EX (12 bits in hdw reg)
+ *              ppppppppplcc0cch        Westmere-EX (12 bits in hdw reg)
+ *              pppppppppppcccch        SandyBridge (15 bits in hdw reg)
  *              sssssssssss
  *
  *                      p  = pnode bits
@@ -86,7 +88,7 @@
  *                      h  = hyperthread
  *                      s  = bits that are in the SOCKET_ID CSR
  *
- *      Note: Processor only supports 12 bits in the APICID register. The ACPI
+ *      Note: Processor may support fewer bits in the APICID register. The ACPI
  *            tables hold all 16 bits. Software needs to be aware of this.
  *
  *            Unless otherwise specified, all references to APICID refer to
@@ -137,6 +139,8 @@ struct uv_hub_info_s {
         unsigned long           global_mmr_base;
         unsigned long           gpa_mask;
         unsigned int            gnode_extra;
+        unsigned char           hub_revision;
+        unsigned char           apic_pnode_shift;
         unsigned long           gnode_upper;
         unsigned long           lowmem_remap_top;
         unsigned long           lowmem_remap_base;
@@ -155,6 +159,37 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_cpu_hub_info(cpu)    (&per_cpu(__uv_hub_info, cpu))
 
 /*
+ * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2
+ * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE.
+ * This is a software convention - NOT the hardware revision numbers in
+ * the hub chip.
+ */
+#define UV1_HUB_REVISION_BASE           1
+#define UV2_HUB_REVISION_BASE           3
+
+static inline int is_uv1_hub(void)
+{
+        return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
+}
+
+static inline int is_uv2_hub(void)
+{
+        return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
+}
+
+union uvh_apicid {
+    unsigned long       v;
+    struct uvh_apicid_s {
+        unsigned long   local_apic_mask  : 24;
+        unsigned long   local_apic_shift :  5;
+        unsigned long   unused1          :  3;
+        unsigned long   pnode_mask       : 24;
+        unsigned long   pnode_shift      :  5;
+        unsigned long   unused2          :  3;
+    } s;
+};
+
+/*
  * Local & Global MMR space macros.
  *      Note: macros are intended to be used ONLY by inline functions
  *      in this file - not by other kernel code.
@@ -166,11 +201,25 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_PNODE_TO_GNODE(p)            ((p) |uv_hub_info->gnode_extra)
 #define UV_PNODE_TO_NASID(p)            (UV_PNODE_TO_GNODE(p) << 1)
 
-#define UV_LOCAL_MMR_BASE               0xf4000000UL
-#define UV_GLOBAL_MMR32_BASE            0xf8000000UL
+#define UV1_LOCAL_MMR_BASE              0xf4000000UL
+#define UV1_GLOBAL_MMR32_BASE           0xf8000000UL
+#define UV1_LOCAL_MMR_SIZE              (64UL * 1024 * 1024)
+#define UV1_GLOBAL_MMR32_SIZE           (64UL * 1024 * 1024)
+
+#define UV2_LOCAL_MMR_BASE              0xfa000000UL
+#define UV2_GLOBAL_MMR32_BASE           0xfc000000UL
+#define UV2_LOCAL_MMR_SIZE              (32UL * 1024 * 1024)
+#define UV2_GLOBAL_MMR32_SIZE           (32UL * 1024 * 1024)
+
+#define UV_LOCAL_MMR_BASE               (is_uv1_hub() ? UV1_LOCAL_MMR_BASE     \
+                                                : UV2_LOCAL_MMR_BASE)
+#define UV_GLOBAL_MMR32_BASE            (is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE  \
+                                                : UV2_GLOBAL_MMR32_BASE)
+#define UV_LOCAL_MMR_SIZE               (is_uv1_hub() ? UV1_LOCAL_MMR_SIZE :   \
+                                                UV2_LOCAL_MMR_SIZE)
+#define UV_GLOBAL_MMR32_SIZE            (is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\
+                                                UV2_GLOBAL_MMR32_SIZE)
 #define UV_GLOBAL_MMR64_BASE            (uv_hub_info->global_mmr_base)
-#define UV_LOCAL_MMR_SIZE               (64UL * 1024 * 1024)
-#define UV_GLOBAL_MMR32_SIZE            (64UL * 1024 * 1024)
 
 #define UV_GLOBAL_GRU_MMR_BASE          0x4000000
 
@@ -182,8 +231,11 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)                                   \
         (((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
+#define UVH_APICID              0x002D0E00L
 #define UV_APIC_PNODE_SHIFT     6
 
+#define UV_APICID_HIBIT_MASK    0xffff0000
+
 /* Local Bus from cpu's perspective */
 #define LOCAL_BUS_BASE          0x1c00000
 #define LOCAL_BUS_SIZE          (4 * 1024 * 1024)
@@ -280,7 +332,18 @@ static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
  */
 static inline int uv_apicid_to_pnode(int apicid)
 {
-        return (apicid >> UV_APIC_PNODE_SHIFT);
+        return (apicid >> uv_hub_info->apic_pnode_shift);
+}
+
+/*
+ * Convert an apicid to the socket number on the blade
+ */
+static inline int uv_apicid_to_socket(int apicid)
+{
+        if (is_uv1_hub())
+                return (apicid >> (uv_hub_info->apic_pnode_shift - 1)) & 1;
+        else
+                return 0;
 }
 
 /*
@@ -381,6 +444,8 @@ struct uv_blade_info {
         unsigned short  nr_online_cpus;
         unsigned short  pnode;
         short           memory_nid;
+        spinlock_t      nmi_lock;
+        unsigned long   nmi_count;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -476,8 +541,10 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
         }
 }
 
+extern unsigned int uv_apicid_hibits;
 static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
 {
+        apicid |= uv_apicid_hibits;
         return (1UL << UVH_IPI_INT_SEND_SHFT) |
                         ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
                         (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
@@ -498,14 +565,13 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
- *     1 - initial rev 1.0 silicon
- *     2 - rev 2.0 production silicon
+ *     1 - UV1 rev 1.0 initial silicon
+ *     2 - UV1 rev 2.0 production silicon
+ *     3 - UV2 rev 1.0 initial silicon
  */
 static inline int uv_get_min_hub_revision_id(void)
 {
-        extern int uv_min_hub_revision_id;
-
-        return uv_min_hub_revision_id;
+        return uv_hub_info->hub_revision;
 }
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index b2f2d2e05cec..4be52c863448 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,19 +5,70 @@
  *
  * SGI UV MMR definitions
  *
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_MMRS_H
 #define _ASM_X86_UV_UV_MMRS_H
 
+/*
+ * This file contains MMR definitions for both UV1 & UV2 hubs.
+ *
+ * In general, MMR addresses and structures are identical on both hubs.
+ * These MMRs are identified as:
+ *      #define UVH_xxx         <address>
+ *      union uvh_xxx {
+ *              unsigned long       v;
+ *              struct uvh_int_cmpd_s {
+ *              } s;
+ *      };
+ *
+ * If the MMR exists on both hub type but has different addresses or
+ * contents, the MMR definition is similar to:
+ *      #define UV1H_xxx        <uv1 address>
+ *      #define UV2H_xxx        <uv2address>
+ *      #define UVH_xxx         (is_uv1_hub() ? UV1H_xxx : UV2H_xxx)
+ *      union uvh_xxx {
+ *              unsigned long       v;
+ *              struct uv1h_int_cmpd_s {         (Common fields only)
+ *              } s;
+ *              struct uv1h_int_cmpd_s {         (Full UV1 definition)
+ *              } s1;
+ *              struct uv2h_int_cmpd_s {         (Full UV2 definition)
+ *              } s2;
+ *      };
+ *
+ * Only essential difference are enumerated. For example, if the address is
+ * the same for both UV1 & UV2, only a single #define is generated. Likewise,
+ * if the contents is the same for both hubs, only the "s" structure is
+ * generated.
+ *
+ * If the MMR exists on ONLY 1 type of hub, no generic definition is
+ * generated:
+ *      #define UVnH_xxx        <uvn address>
+ *      union uvnh_xxx {
+ *              unsigned long       v;
+ *              struct uvh_int_cmpd_s {
+ *              } sn;
+ *      };
+ */
+
 #define UV_MMR_ENABLE           (1UL << 63)
 
+#define UV1_HUB_PART_NUMBER     0x88a5
+#define UV2_HUB_PART_NUMBER     0x8eb8
+
+/* Compat: if this #define is present, UV headers support UV2 */
+#define UV2_HUB_IS_SUPPORTED    1
+
+/* KABI compat: if this #define is present, KABI hacks are present */
+#define UV2_HUB_KABI_HACKS      1
+
 /* ========================================================================= */
 /*                          UVH_BAU_DATA_BROADCAST                           */
 /* ========================================================================= */
 #define UVH_BAU_DATA_BROADCAST 0x61688UL
-#define UVH_BAU_DATA_BROADCAST_32 0x0440
+#define UVH_BAU_DATA_BROADCAST_32 0x440
 
 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0
 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL
@@ -34,7 +85,7 @@ union uvh_bau_data_broadcast_u {
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
-#define UVH_BAU_DATA_CONFIG_32 0x0438
+#define UVH_BAU_DATA_CONFIG_32 0x438
 
 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
 #define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
@@ -73,125 +124,245 @@ union uvh_bau_data_config_u {
 /*                           UVH_EVENT_OCCURRED0                             */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0 0x70000UL
-#define UVH_EVENT_OCCURRED0_32 0x005e8
-
-#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
-#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
-#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
-#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
-#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
-#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
-#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
-#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
-#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
-#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
-#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
-#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
-#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
-#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+#define UVH_EVENT_OCCURRED0_32 0x5e8
+
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UV1H_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UV1H_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UV1H_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UV1H_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UV1H_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UV1H_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UV1H_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UV1H_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_SHFT 2
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_SHFT 3
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_SHFT 4
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_SHFT 5
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_SHFT 6
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_SHFT 7
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_SHFT 8
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_SHFT 9
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_SHFT 16
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL
+#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53
+#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL
+
 union uvh_event_occurred0_u {
     unsigned long       v;
-    struct uvh_event_occurred0_s {
+    struct uv1h_event_occurred0_s {
         unsigned long   lb_hcerr             :  1;  /* RW, W1C */
         unsigned long   gr0_hcerr            :  1;  /* RW, W1C */
         unsigned long   gr1_hcerr            :  1;  /* RW, W1C */
@@ -250,14 +421,76 @@ union uvh_event_occurred0_u {
         unsigned long   bau_data             :  1;  /* RW, W1C */
         unsigned long   power_management_req :  1;  /* RW, W1C */
         unsigned long   rsvd_57_63           :  7;  /*    */
-    } s;
+    } s1;
+    struct uv2h_event_occurred0_s {
+        unsigned long   lb_hcerr            :  1;  /* RW */
+        unsigned long   qp_hcerr            :  1;  /* RW */
+        unsigned long   rh_hcerr            :  1;  /* RW */
+        unsigned long   lh0_hcerr           :  1;  /* RW */
+        unsigned long   lh1_hcerr           :  1;  /* RW */
+        unsigned long   gr0_hcerr           :  1;  /* RW */
+        unsigned long   gr1_hcerr           :  1;  /* RW */
+        unsigned long   ni0_hcerr           :  1;  /* RW */
+        unsigned long   ni1_hcerr           :  1;  /* RW */
+        unsigned long   lb_aoerr0           :  1;  /* RW */
+        unsigned long   qp_aoerr0           :  1;  /* RW */
+        unsigned long   rh_aoerr0           :  1;  /* RW */
+        unsigned long   lh0_aoerr0          :  1;  /* RW */
+        unsigned long   lh1_aoerr0          :  1;  /* RW */
+        unsigned long   gr0_aoerr0          :  1;  /* RW */
+        unsigned long   gr1_aoerr0          :  1;  /* RW */
+        unsigned long   xb_aoerr0           :  1;  /* RW */
+        unsigned long   rt_aoerr0           :  1;  /* RW */
+        unsigned long   ni0_aoerr0          :  1;  /* RW */
+        unsigned long   ni1_aoerr0          :  1;  /* RW */
+        unsigned long   lb_aoerr1           :  1;  /* RW */
+        unsigned long   qp_aoerr1           :  1;  /* RW */
+        unsigned long   rh_aoerr1           :  1;  /* RW */
+        unsigned long   lh0_aoerr1          :  1;  /* RW */
+        unsigned long   lh1_aoerr1          :  1;  /* RW */
+        unsigned long   gr0_aoerr1          :  1;  /* RW */
+        unsigned long   gr1_aoerr1          :  1;  /* RW */
+        unsigned long   xb_aoerr1           :  1;  /* RW */
+        unsigned long   rt_aoerr1           :  1;  /* RW */
+        unsigned long   ni0_aoerr1          :  1;  /* RW */
+        unsigned long   ni1_aoerr1          :  1;  /* RW */
+        unsigned long   system_shutdown_int :  1;  /* RW */
+        unsigned long   lb_irq_int_0        :  1;  /* RW */
+        unsigned long   lb_irq_int_1        :  1;  /* RW */
+        unsigned long   lb_irq_int_2        :  1;  /* RW */
+        unsigned long   lb_irq_int_3        :  1;  /* RW */
+        unsigned long   lb_irq_int_4        :  1;  /* RW */
+        unsigned long   lb_irq_int_5        :  1;  /* RW */
+        unsigned long   lb_irq_int_6        :  1;  /* RW */
+        unsigned long   lb_irq_int_7        :  1;  /* RW */
+        unsigned long   lb_irq_int_8        :  1;  /* RW */
+        unsigned long   lb_irq_int_9        :  1;  /* RW */
+        unsigned long   lb_irq_int_10       :  1;  /* RW */
+        unsigned long   lb_irq_int_11       :  1;  /* RW */
+        unsigned long   lb_irq_int_12       :  1;  /* RW */
+        unsigned long   lb_irq_int_13       :  1;  /* RW */
+        unsigned long   lb_irq_int_14       :  1;  /* RW */
+        unsigned long   lb_irq_int_15       :  1;  /* RW */
+        unsigned long   l1_nmi_int          :  1;  /* RW */
+        unsigned long   stop_clock          :  1;  /* RW */
+        unsigned long   asic_to_l1          :  1;  /* RW */
+        unsigned long   l1_to_asic          :  1;  /* RW */
+        unsigned long   la_seq_trigger      :  1;  /* RW */
+        unsigned long   ipi_int             :  1;  /* RW */
+        unsigned long   extio_int0          :  1;  /* RW */
+        unsigned long   extio_int1          :  1;  /* RW */
+        unsigned long   extio_int2          :  1;  /* RW */
+        unsigned long   extio_int3          :  1;  /* RW */
+        unsigned long   profile_int         :  1;  /* RW */
+        unsigned long   rsvd_59_63          :  5;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                        UVH_EVENT_OCCURRED0_ALIAS                          */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
-#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0
 
 /* ========================================================================= */
 /*                         UVH_GR0_TLB_INT0_CONFIG                           */
@@ -432,8 +665,16 @@ union uvh_int_cmpb_u {
 /* ========================================================================= */
 #define UVH_INT_CMPC 0x22100UL
 
-#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
-#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT       0
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT       0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT :     \
+                        UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT)
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK       0xffffffffffffffUL
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_MASK       0xffffffffffffffUL
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPC_REAL_TIME_CMPC_MASK :     \
+                        UV2H_INT_CMPC_REAL_TIME_CMPC_MASK)
 
 union uvh_int_cmpc_u {
     unsigned long       v;
@@ -448,8 +689,16 @@ union uvh_int_cmpc_u {
 /* ========================================================================= */
 #define UVH_INT_CMPD 0x22180UL
 
-#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
-#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT       0
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT       0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT :     \
+                        UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT)
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK       0xffffffffffffffUL
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_MASK       0xffffffffffffffUL
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPD_REAL_TIME_CMPD_MASK :     \
+                        UV2H_INT_CMPD_REAL_TIME_CMPD_MASK)
 
 union uvh_int_cmpd_u {
     unsigned long       v;
@@ -463,7 +712,7 @@ union uvh_int_cmpd_u {
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0348
+#define UVH_IPI_INT_32 0x348
 
 #define UVH_IPI_INT_VECTOR_SHFT 0
 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
@@ -493,7 +742,7 @@ union uvh_ipi_int_u {
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -515,7 +764,7 @@ union uvh_lb_bau_intd_payload_queue_first_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -533,7 +782,7 @@ union uvh_lb_bau_intd_payload_queue_last_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
@@ -551,7 +800,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68
 
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
@@ -585,6 +834,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
 union uvh_lb_bau_intd_software_acknowledge_u {
     unsigned long       v;
     struct uvh_lb_bau_intd_software_acknowledge_s {
@@ -612,13 +862,13 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70
 
 /* ========================================================================= */
 /*                         UVH_LB_BAU_MISC_CONTROL                           */
 /* ========================================================================= */
 #define UVH_LB_BAU_MISC_CONTROL 0x320170UL
-#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10
+#define UVH_LB_BAU_MISC_CONTROL_32 0xa10
 
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
@@ -628,8 +878,8 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
@@ -650,8 +900,86 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
-#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48
-#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
 
 union uvh_lb_bau_misc_control_u {
     unsigned long       v;
@@ -660,7 +988,25 @@ union uvh_lb_bau_misc_control_u {
         unsigned long   apic_mode                          :  1;  /* RW */
         unsigned long   force_broadcast                    :  1;  /* RW */
         unsigned long   force_lock_nop                     :  1;  /* RW */
-        unsigned long   csi_agent_presence_vector          :  3;  /* RW */
+        unsigned long   qpi_agent_presence_vector          :  3;  /* RW */
+        unsigned long   descriptor_fetch_mode              :  1;  /* RW */
+        unsigned long   enable_intd_soft_ack_mode          :  1;  /* RW */
+        unsigned long   intd_soft_ack_timeout_period       :  4;  /* RW */
+        unsigned long   enable_dual_mapping_mode           :  1;  /* RW */
+        unsigned long   vga_io_port_decode_enable          :  1;  /* RW */
+        unsigned long   vga_io_port_16_bit_decode          :  1;  /* RW */
+        unsigned long   suppress_dest_registration         :  1;  /* RW */
+        unsigned long   programmed_initial_priority        :  3;  /* RW */
+        unsigned long   use_incoming_priority              :  1;  /* RW */
+        unsigned long   enable_programmed_initial_priority :  1;  /* RW */
+        unsigned long   rsvd_29_63    : 35;
+    } s;
+    struct uv1h_lb_bau_misc_control_s {
+        unsigned long   rejection_delay                    :  8;  /* RW */
+        unsigned long   apic_mode                          :  1;  /* RW */
+        unsigned long   force_broadcast                    :  1;  /* RW */
+        unsigned long   force_lock_nop                     :  1;  /* RW */
+        unsigned long   qpi_agent_presence_vector          :  3;  /* RW */
         unsigned long   descriptor_fetch_mode              :  1;  /* RW */
         unsigned long   enable_intd_soft_ack_mode          :  1;  /* RW */
         unsigned long   intd_soft_ack_timeout_period       :  4;  /* RW */
@@ -673,14 +1019,40 @@ union uvh_lb_bau_misc_control_u {
         unsigned long   enable_programmed_initial_priority :  1;  /* RW */
         unsigned long   rsvd_29_47                         : 19;  /*    */
         unsigned long   fun                                : 16;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_lb_bau_misc_control_s {
+        unsigned long   rejection_delay                      :  8;  /* RW */
+        unsigned long   apic_mode                            :  1;  /* RW */
+        unsigned long   force_broadcast                      :  1;  /* RW */
+        unsigned long   force_lock_nop                       :  1;  /* RW */
+        unsigned long   qpi_agent_presence_vector            :  3;  /* RW */
+        unsigned long   descriptor_fetch_mode                :  1;  /* RW */
+        unsigned long   enable_intd_soft_ack_mode            :  1;  /* RW */
+        unsigned long   intd_soft_ack_timeout_period         :  4;  /* RW */
+        unsigned long   enable_dual_mapping_mode             :  1;  /* RW */
+        unsigned long   vga_io_port_decode_enable            :  1;  /* RW */
+        unsigned long   vga_io_port_16_bit_decode            :  1;  /* RW */
+        unsigned long   suppress_dest_registration           :  1;  /* RW */
+        unsigned long   programmed_initial_priority          :  3;  /* RW */
+        unsigned long   use_incoming_priority                :  1;  /* RW */
+        unsigned long   enable_programmed_initial_priority   :  1;  /* RW */
+        unsigned long   enable_automatic_apic_mode_selection :  1;  /* RW */
+        unsigned long   apic_mode_status                     :  1;  /* RO */
+        unsigned long   suppress_interrupts_to_self          :  1;  /* RW */
+        unsigned long   enable_lock_based_system_flush       :  1;  /* RW */
+        unsigned long   enable_extended_sb_status            :  1;  /* RW */
+        unsigned long   suppress_int_prio_udt_to_self        :  1;  /* RW */
+        unsigned long   use_legacy_descriptor_formats        :  1;  /* RW */
+        unsigned long   rsvd_36_47                           : 12;  /*    */
+        unsigned long   fun                                  : 16;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
@@ -703,7 +1075,7 @@ union uvh_lb_bau_sb_activation_control_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
@@ -719,7 +1091,7 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
@@ -735,7 +1107,7 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
@@ -768,10 +1140,36 @@ union uvh_lb_bau_sb_descriptor_base_u {
 #define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL
 #define UVH_NODE_ID_NODE_ID_SHFT 32
 #define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
-#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48
-#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
-#define UVH_NODE_ID_NI_PORT_SHFT 56
-#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV1H_NODE_ID_FORCE1_SHFT 0
+#define UV1H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV1H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV1H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV1H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV1H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV1H_NODE_ID_REVISION_SHFT 28
+#define UV1H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV1H_NODE_ID_NODE_ID_SHFT 32
+#define UV1H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV1H_NODE_ID_NODES_PER_BIT_SHFT 48
+#define UV1H_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
+#define UV1H_NODE_ID_NI_PORT_SHFT 56
+#define UV1H_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV2H_NODE_ID_FORCE1_SHFT 0
+#define UV2H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV2H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV2H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV2H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV2H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV2H_NODE_ID_REVISION_SHFT 28
+#define UV2H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV2H_NODE_ID_NODE_ID_SHFT 32
+#define UV2H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV2H_NODE_ID_NODES_PER_BIT_SHFT 50
+#define UV2H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL
+#define UV2H_NODE_ID_NI_PORT_SHFT 57
+#define UV2H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL
 
 union uvh_node_id_u {
     unsigned long       v;
@@ -781,12 +1179,31 @@ union uvh_node_id_u {
         unsigned long   part_number   : 16;  /* RO */
         unsigned long   revision      :  4;  /* RO */
         unsigned long   node_id       : 15;  /* RW */
+        unsigned long   rsvd_47_63    : 17;
+    } s;
+    struct uv1h_node_id_s {
+        unsigned long   force1        :  1;  /* RO */
+        unsigned long   manufacturer  : 11;  /* RO */
+        unsigned long   part_number   : 16;  /* RO */
+        unsigned long   revision      :  4;  /* RO */
+        unsigned long   node_id       : 15;  /* RW */
         unsigned long   rsvd_47       :  1;  /*    */
         unsigned long   nodes_per_bit :  7;  /* RW */
         unsigned long   rsvd_55       :  1;  /*    */
         unsigned long   ni_port       :  4;  /* RO */
         unsigned long   rsvd_60_63    :  4;  /*    */
-    } s;
+    } s1;
+    struct uv2h_node_id_s {
+        unsigned long   force1        :  1;  /* RO */
+        unsigned long   manufacturer  : 11;  /* RO */
+        unsigned long   part_number   : 16;  /* RO */
+        unsigned long   revision      :  4;  /* RO */
+        unsigned long   node_id       : 15;  /* RW */
+        unsigned long   rsvd_47_49    :  3;  /*    */
+        unsigned long   nodes_per_bit :  7;  /* RO */
+        unsigned long   ni_port       :  5;  /* RO */
+        unsigned long   rsvd_62_63    :  2;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -806,6 +1223,78 @@ union uvh_node_present_table_u {
 };
 
 /* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_overlay_config_0_mmr_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_overlay_config_1_mmr_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_alias210_overlay_config_2_mmr_s {
+        unsigned long   rsvd_0_23: 24;  /*    */
+        unsigned long   base    :  8;  /* RW */
+        unsigned long   rsvd_32_47: 16;  /*    */
+        unsigned long   m_alias :  5;  /* RW */
+        unsigned long   rsvd_53_62: 10;  /*    */
+        unsigned long   enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
 /* ========================================================================= */
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
@@ -857,31 +1346,98 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 };
 
 /* ========================================================================= */
+/*                          UVH_RH_GAM_CONFIG_MMR                            */
+/* ========================================================================= */
+#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL
+
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+
+union uvh_rh_gam_config_mmr_u {
+    unsigned long       v;
+    struct uvh_rh_gam_config_mmr_s {
+        unsigned long   m_skt     :  6;  /* RW */
+        unsigned long   n_skt     :  4;  /* RW */
+        unsigned long   rsvd_10_63    : 54;
+    } s;
+    struct uv1h_rh_gam_config_mmr_s {
+        unsigned long   m_skt     :  6;  /* RW */
+        unsigned long   n_skt     :  4;  /* RW */
+        unsigned long   rsvd_10_11:  2;  /*    */
+        unsigned long   mmiol_cfg :  1;  /* RW */
+        unsigned long   rsvd_13_63: 51;  /*    */
+    } s1;
+    struct uv2h_rh_gam_config_mmr_s {
+        unsigned long   m_skt :  6;  /* RW */
+        unsigned long   n_skt :  4;  /* RW */
+        unsigned long   rsvd_10_63: 54;  /*    */
+    } s2;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
 
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_gru_overlay_config_mmr_u {
     unsigned long       v;
     struct uvh_rh_gam_gru_overlay_config_mmr_s {
         unsigned long   rsvd_0_27: 28;  /*    */
         unsigned long   base   : 18;  /* RW */
+        unsigned long   rsvd_46_62    : 17;
+        unsigned long   enable :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_gru_overlay_config_mmr_s {
+        unsigned long   rsvd_0_27: 28;  /*    */
+        unsigned long   base   : 18;  /* RW */
         unsigned long   rsvd_46_47:  2;  /*    */
         unsigned long   gr4    :  1;  /* RW */
         unsigned long   rsvd_49_51:  3;  /*    */
         unsigned long   n_gru  :  4;  /* RW */
         unsigned long   rsvd_56_62:  7;  /*    */
         unsigned long   enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_gru_overlay_config_mmr_s {
+        unsigned long   rsvd_0_27: 28;  /*    */
+        unsigned long   base   : 18;  /* RW */
+        unsigned long   rsvd_46_51:  6;  /*    */
+        unsigned long   n_gru  :  4;  /* RW */
+        unsigned long   rsvd_56_62:  7;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -889,25 +1445,42 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 /* ========================================================================= */
 #define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
 
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 27
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff8000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmioh_overlay_config_mmr_u {
     unsigned long       v;
-    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+    struct uv1h_rh_gam_mmioh_overlay_config_mmr_s {
         unsigned long   rsvd_0_29: 30;  /*    */
         unsigned long   base   : 16;  /* RW */
         unsigned long   m_io   :  6;  /* RW */
         unsigned long   n_io   :  4;  /* RW */
         unsigned long   rsvd_56_62:  7;  /*    */
         unsigned long   enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmioh_overlay_config_mmr_s {
+        unsigned long   rsvd_0_26: 27;  /*    */
+        unsigned long   base   : 19;  /* RW */
+        unsigned long   m_io   :  6;  /* RW */
+        unsigned long   n_io   :  4;  /* RW */
+        unsigned long   rsvd_56_62:  7;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -917,20 +1490,40 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmr_overlay_config_mmr_u {
     unsigned long       v;
     struct uvh_rh_gam_mmr_overlay_config_mmr_s {
         unsigned long   rsvd_0_25: 26;  /*    */
         unsigned long   base     : 20;  /* RW */
+        unsigned long   rsvd_46_62    : 17;
+        unsigned long   enable   :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_mmr_overlay_config_mmr_s {
+        unsigned long   rsvd_0_25: 26;  /*    */
+        unsigned long   base     : 20;  /* RW */
         unsigned long   dual_hub :  1;  /* RW */
         unsigned long   rsvd_47_62: 16;  /*    */
         unsigned long   enable   :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmr_overlay_config_mmr_s {
+        unsigned long   rsvd_0_25: 26;  /*    */
+        unsigned long   base   : 20;  /* RW */
+        unsigned long   rsvd_46_62: 17;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -988,96 +1581,169 @@ union uvh_rtc1_int_config_u {
 };
 
 /* ========================================================================= */
-/*                          UVH_SI_ADDR_MAP_CONFIG                           */
+/*                               UVH_SCRATCH5                                */
 /* ========================================================================= */
-#define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
+#define UVH_SCRATCH5 0x2d0200UL
+#define UVH_SCRATCH5_32 0x778
 
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_SHFT 0
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_SHFT 8
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_MASK 0x0000000000000f00UL
+#define UVH_SCRATCH5_SCRATCH5_SHFT 0
+#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
 
-union uvh_si_addr_map_config_u {
+union uvh_scratch5_u {
     unsigned long       v;
-    struct uvh_si_addr_map_config_s {
-        unsigned long   m_skt :  6;  /* RW */
-        unsigned long   rsvd_6_7:  2;  /*    */
-        unsigned long   n_skt :  4;  /* RW */
-        unsigned long   rsvd_12_63: 52;  /*    */
+    struct uvh_scratch5_s {
+        unsigned long   scratch5 : 64;  /* RW, W1CS */
     } s;
 };
 
 /* ========================================================================= */
-/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
-
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias0_overlay_config_u {
+/*                           UV2H_EVENT_OCCURRED2                            */
+/* ========================================================================= */
+#define UV2H_EVENT_OCCURRED2 0x70100UL
+#define UV2H_EVENT_OCCURRED2_32 0xb68
+
+#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0
+#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1
+#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2
+#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3
+#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4
+#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5
+#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6
+#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7
+#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8
+#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9
+#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10
+#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11
+#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12
+#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13
+#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14
+#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15
+#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16
+#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17
+#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18
+#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19
+#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20
+#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21
+#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22
+#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23
+#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24
+#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25
+#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26
+#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27
+#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28
+#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29
+#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30
+#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31
+#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL
+
+union uv2h_event_occurred2_u {
     unsigned long       v;
-    struct uvh_si_alias0_overlay_config_s {
-        unsigned long   rsvd_0_23: 24;  /*    */
-        unsigned long   base    :  8;  /* RW */
-        unsigned long   rsvd_32_47: 16;  /*    */
-        unsigned long   m_alias :  5;  /* RW */
-        unsigned long   rsvd_53_62: 10;  /*    */
-        unsigned long   enable  :  1;  /* RW */
-    } s;
+    struct uv2h_event_occurred2_s {
+        unsigned long   rtc_0  :  1;  /* RW */
+        unsigned long   rtc_1  :  1;  /* RW */
+        unsigned long   rtc_2  :  1;  /* RW */
+        unsigned long   rtc_3  :  1;  /* RW */
+        unsigned long   rtc_4  :  1;  /* RW */
+        unsigned long   rtc_5  :  1;  /* RW */
+        unsigned long   rtc_6  :  1;  /* RW */
+        unsigned long   rtc_7  :  1;  /* RW */
+        unsigned long   rtc_8  :  1;  /* RW */
+        unsigned long   rtc_9  :  1;  /* RW */
+        unsigned long   rtc_10 :  1;  /* RW */
+        unsigned long   rtc_11 :  1;  /* RW */
+        unsigned long   rtc_12 :  1;  /* RW */
+        unsigned long   rtc_13 :  1;  /* RW */
+        unsigned long   rtc_14 :  1;  /* RW */
+        unsigned long   rtc_15 :  1;  /* RW */
+        unsigned long   rtc_16 :  1;  /* RW */
+        unsigned long   rtc_17 :  1;  /* RW */
+        unsigned long   rtc_18 :  1;  /* RW */
+        unsigned long   rtc_19 :  1;  /* RW */
+        unsigned long   rtc_20 :  1;  /* RW */
+        unsigned long   rtc_21 :  1;  /* RW */
+        unsigned long   rtc_22 :  1;  /* RW */
+        unsigned long   rtc_23 :  1;  /* RW */
+        unsigned long   rtc_24 :  1;  /* RW */
+        unsigned long   rtc_25 :  1;  /* RW */
+        unsigned long   rtc_26 :  1;  /* RW */
+        unsigned long   rtc_27 :  1;  /* RW */
+        unsigned long   rtc_28 :  1;  /* RW */
+        unsigned long   rtc_29 :  1;  /* RW */
+        unsigned long   rtc_30 :  1;  /* RW */
+        unsigned long   rtc_31 :  1;  /* RW */
+        unsigned long   rsvd_32_63: 32;  /*    */
+    } s1;
 };
 
 /* ========================================================================= */
-/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
+/*                        UV2H_EVENT_OCCURRED2_ALIAS                         */
 /* ========================================================================= */
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
+#define UV2H_EVENT_OCCURRED2_ALIAS 0x70108UL
+#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70
 
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+/* ========================================================================= */
+/*                    UV2H_LB_BAU_SB_ACTIVATION_STATUS_2                     */
+/* ========================================================================= */
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
 
-union uvh_si_alias1_overlay_config_u {
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
+
+union uv2h_lb_bau_sb_activation_status_2_u {
     unsigned long       v;
-    struct uvh_si_alias1_overlay_config_s {
-        unsigned long   rsvd_0_23: 24;  /*    */
-        unsigned long   base    :  8;  /* RW */
-        unsigned long   rsvd_32_47: 16;  /*    */
-        unsigned long   m_alias :  5;  /* RW */
-        unsigned long   rsvd_53_62: 10;  /*    */
-        unsigned long   enable  :  1;  /* RW */
-    } s;
+    struct uv2h_lb_bau_sb_activation_status_2_s {
+        unsigned long   aux_error : 64;  /* RW */
+    } s1;
 };
 
 /* ========================================================================= */
-/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
+/*                   UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK                    */
 /* ========================================================================= */
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x9f0
 
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
 
-union uvh_si_alias2_overlay_config_u {
+union uv1h_lb_target_physical_apic_id_mask_u {
     unsigned long       v;
-    struct uvh_si_alias2_overlay_config_s {
-        unsigned long   rsvd_0_23: 24;  /*    */
-        unsigned long   base    :  8;  /* RW */
-        unsigned long   rsvd_32_47: 16;  /*    */
-        unsigned long   m_alias :  5;  /* RW */
-        unsigned long   rsvd_53_62: 10;  /*    */
-        unsigned long   enable  :  1;  /* RW */
-    } s;
+    struct uv1h_lb_target_physical_apic_id_mask_s {
+        unsigned long   bit_enables : 32;  /* RW */
+        unsigned long   rsvd_32_63  : 32;  /*    */
+    } s1;
 };
 
 
-#endif /* _ASM_X86_UV_UV_MMRS_H */
+#endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 9064052b73de..bb0522850b74 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -1,20 +1,6 @@
 #ifndef _ASM_X86_VDSO_H
 #define _ASM_X86_VDSO_H
 
-#ifdef CONFIG_X86_64
-extern const char VDSO64_PRELINK[];
-
-/*
- * Given a pointer to the vDSO image, find the pointer to VDSO64_name
- * as that symbol is defined in the vDSO sources or linker script.
- */
-#define VDSO64_SYMBOL(base, name)                                       \
-({                                                                      \
-        extern const char VDSO64_##name[];                              \
-        (void *)(VDSO64_##name - VDSO64_PRELINK + (unsigned long)(base)); \
-})
-#endif
-
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
 extern const char VDSO32_PRELINK[];
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 3d61e204826f..646b4c1ca695 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -23,8 +23,6 @@ struct vsyscall_gtod_data {
         struct timespec wall_to_monotonic;
         struct timespec wall_time_coarse;
 };
-extern struct vsyscall_gtod_data __vsyscall_gtod_data
-__section_vsyscall_gtod_data;
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
 #endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
deleted file mode 100644
index 61e08c0a2907..000000000000
--- a/arch/x86/include/asm/vmi.h
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * VMI interface definition
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Maintained by: Zachary Amsden zach@vmware.com
- *
- */
-#include <linux/types.h>
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI Option ROM API
- *
- *---------------------------------------------------------------------
- */
-#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
-
-#define PCI_VENDOR_ID_VMWARE            0x15AD
-#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
-
-/*
- * We use two version numbers for compatibility, with the major
- * number signifying interface breakages, and the minor number
- * interface extensions.
- */
-#define VMI_API_REV_MAJOR       3
-#define VMI_API_REV_MINOR       0
-
-#define VMI_CALL_CPUID                  0
-#define VMI_CALL_WRMSR                  1
-#define VMI_CALL_RDMSR                  2
-#define VMI_CALL_SetGDT                 3
-#define VMI_CALL_SetLDT                 4
-#define VMI_CALL_SetIDT                 5
-#define VMI_CALL_SetTR                  6
-#define VMI_CALL_GetGDT                 7
-#define VMI_CALL_GetLDT                 8
-#define VMI_CALL_GetIDT                 9
-#define VMI_CALL_GetTR                  10
-#define VMI_CALL_WriteGDTEntry          11
-#define VMI_CALL_WriteLDTEntry          12
-#define VMI_CALL_WriteIDTEntry          13
-#define VMI_CALL_UpdateKernelStack      14
-#define VMI_CALL_SetCR0                 15
-#define VMI_CALL_SetCR2                 16
-#define VMI_CALL_SetCR3                 17
-#define VMI_CALL_SetCR4                 18
-#define VMI_CALL_GetCR0                 19
-#define VMI_CALL_GetCR2                 20
-#define VMI_CALL_GetCR3                 21
-#define VMI_CALL_GetCR4                 22
-#define VMI_CALL_WBINVD                 23
-#define VMI_CALL_SetDR                  24
-#define VMI_CALL_GetDR                  25
-#define VMI_CALL_RDPMC                  26
-#define VMI_CALL_RDTSC                  27
-#define VMI_CALL_CLTS                   28
-#define VMI_CALL_EnableInterrupts       29
-#define VMI_CALL_DisableInterrupts      30
-#define VMI_CALL_GetInterruptMask       31
-#define VMI_CALL_SetInterruptMask       32
-#define VMI_CALL_IRET                   33
-#define VMI_CALL_SYSEXIT                34
-#define VMI_CALL_Halt                   35
-#define VMI_CALL_Reboot                 36
-#define VMI_CALL_Shutdown               37
-#define VMI_CALL_SetPxE                 38
-#define VMI_CALL_SetPxELong             39
-#define VMI_CALL_UpdatePxE              40
-#define VMI_CALL_UpdatePxELong          41
-#define VMI_CALL_MachineToPhysical      42
-#define VMI_CALL_PhysicalToMachine      43
-#define VMI_CALL_AllocatePage           44
-#define VMI_CALL_ReleasePage            45
-#define VMI_CALL_InvalPage              46
-#define VMI_CALL_FlushTLB               47
-#define VMI_CALL_SetLinearMapping       48
-
-#define VMI_CALL_SetIOPLMask            61
-#define VMI_CALL_SetInitialAPState      62
-#define VMI_CALL_APICWrite              63
-#define VMI_CALL_APICRead               64
-#define VMI_CALL_IODelay                65
-#define VMI_CALL_SetLazyMode            73
-
-/*
- *---------------------------------------------------------------------
- *
- * MMU operation flags
- *
- *---------------------------------------------------------------------
- */
-
-/* Flags used by VMI_{Allocate|Release}Page call */
-#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
-#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
-#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
-
-
-/* Flags shared by Allocate|Release Page and PTE updates */
-#define VMI_PAGE_PT              0x01
-#define VMI_PAGE_PD              0x02
-#define VMI_PAGE_PDP             0x04
-#define VMI_PAGE_PML4            0x08
-
-#define VMI_PAGE_NORMAL          0x00 /* for debugging */
-
-/* Flags used by PTE updates */
-#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
-#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
-#define VMI_PAGE_VA_MASK         0xfffff000
-
-#ifdef CONFIG_X86_PAE
-#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#else
-#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_ZEROED)
-#endif
-
-/* Flags used by VMI_FlushTLB call */
-#define VMI_FLUSH_TLB            0x01
-#define VMI_FLUSH_GLOBAL         0x02
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI relocation definitions for ROM call get_reloc
- *
- *---------------------------------------------------------------------
- */
-
-/* VMI Relocation types */
-#define VMI_RELOCATION_NONE     0
-#define VMI_RELOCATION_CALL_REL 1
-#define VMI_RELOCATION_JUMP_REL 2
-#define VMI_RELOCATION_NOP      3
-
-#ifndef __ASSEMBLY__
-struct vmi_relocation_info {
-        unsigned char           *eip;
-        unsigned char           type;
-        unsigned char           reserved[3];
-};
-#endif
-
-
-/*
- *---------------------------------------------------------------------
- *
- *  Generic ROM structures and definitions
- *
- *---------------------------------------------------------------------
- */
-
-#ifndef __ASSEMBLY__
-
-struct vrom_header {
-        u16     rom_signature;  /* option ROM signature */
-        u8      rom_length;     /* ROM length in 512 byte chunks */
-        u8      rom_entry[4];   /* 16-bit code entry point */
-        u8      rom_pad0;       /* 4-byte align pad */
-        u32     vrom_signature; /* VROM identification signature */
-        u8      api_version_min;/* Minor version of API */
-        u8      api_version_maj;/* Major version of API */
-        u8      jump_slots;     /* Number of jump slots */
-        u8      reserved1;      /* Reserved for expansion */
-        u32     virtual_top;    /* Hypervisor virtual address start */
-        u16     reserved2;      /* Reserved for expansion */
-        u16     license_offs;   /* Offset to License string */
-        u16     pci_header_offs;/* Offset to PCI OPROM header */
-        u16     pnp_header_offs;/* Offset to PnP OPROM header */
-        u32     rom_pad3;       /* PnP reserverd / VMI reserved */
-        u8      reserved[96];   /* Reserved for headers */
-        char    vmi_init[8];    /* VMI_Init jump point */
-        char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
-} __attribute__((packed));
-
-struct pnp_header {
-        char sig[4];
-        char rev;
-        char size;
-        short next;
-        short res;
-        long devID;
-        unsigned short manufacturer_offset;
-        unsigned short product_offset;
-} __attribute__((packed));
-
-struct pci_header {
-        char sig[4];
-        short vendorID;
-        short deviceID;
-        short vpdData;
-        short size;
-        char rev;
-        char class;
-        char subclass;
-        char interface;
-        short chunks;
-        char rom_version_min;
-        char rom_version_maj;
-        char codetype;
-        char lastRom;
-        short reserved;
-} __attribute__((packed));
-
-/* Function prototypes for bootstrapping */
-#ifdef CONFIG_VMI
-extern void vmi_init(void);
-extern void vmi_activate(void);
-extern void vmi_bringup(void);
-#else
-static inline void vmi_init(void) {}
-static inline void vmi_activate(void) {}
-static inline void vmi_bringup(void) {}
-#endif
-
-/* State needed to start an application processor in an SMP system. */
-struct vmi_ap_state {
-        u32 cr0;
-        u32 cr2;
-        u32 cr3;
-        u32 cr4;
-
-        u64 efer;
-
-        u32 eip;
-        u32 eflags;
-        u32 eax;
-        u32 ebx;
-        u32 ecx;
-        u32 edx;
-        u32 esp;
-        u32 ebp;
-        u32 esi;
-        u32 edi;
-        u16 cs;
-        u16 ss;
-        u16 ds;
-        u16 es;
-        u16 fs;
-        u16 gs;
-        u16 ldtr;
-
-        u16 gdtr_limit;
-        u32 gdtr_base;
-        u32 idtr_base;
-        u16 idtr_limit;
-};
-
-#endif
diff --git a/arch/x86/include/asm/vmi_time.h b/arch/x86/include/asm/vmi_time.h
deleted file mode 100644
index c6e0bee93e3c..000000000000
--- a/arch/x86/include/asm/vmi_time.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * VMI Time wrappers
- *
- * Copyright (C) 2006, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-#ifndef _ASM_X86_VMI_TIME_H
-#define _ASM_X86_VMI_TIME_H
-
-/*
- * Raw VMI call indices for timer functions
- */
-#define VMI_CALL_GetCycleFrequency      66
-#define VMI_CALL_GetCycleCounter        67
-#define VMI_CALL_SetAlarm               68
-#define VMI_CALL_CancelAlarm            69
-#define VMI_CALL_GetWallclockTime       70
-#define VMI_CALL_WallclockUpdated       71
-
-/* Cached VMI timer operations */
-extern struct vmi_timer_ops {
-        u64 (*get_cycle_frequency)(void);
-        u64 (*get_cycle_counter)(int);
-        u64 (*get_wallclock)(void);
-        int (*wallclock_updated)(void);
-        void (*set_alarm)(u32 flags, u64 expiry, u64 period);
-        void (*cancel_alarm)(u32 flags);
-} vmi_timer_ops;
-
-/* Prototypes */
-extern void __init vmi_time_init(void);
-extern unsigned long vmi_get_wallclock(void);
-extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_tsc_khz(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-extern void __devinit vmi_time_bsp_init(void);
-extern void __devinit vmi_time_ap_init(void);
-#endif
-
-/*
- * When run under a hypervisor, a vcpu is always in one of three states:
- * running, halted, or ready.  The vcpu is in the 'running' state if it
- * is executing.  When the vcpu executes the halt interface, the vcpu
- * enters the 'halted' state and remains halted until there is some work
- * pending for the vcpu (e.g. an alarm expires, host I/O completes on
- * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
- * state (waiting for the hypervisor to reschedule it).  Finally, at any
- * time when the vcpu is not in the 'running' state nor the 'halted'
- * state, it is in the 'ready' state.
- *
- * Real time is advances while the vcpu is 'running', 'ready', or
- * 'halted'.  Stolen time is the time in which the vcpu is in the
- * 'ready' state.  Available time is the remaining time -- the vcpu is
- * either 'running' or 'halted'.
- *
- * All three views of time are accessible through the VMI cycle
- * counters.
- */
-
-/* The cycle counters. */
-#define VMI_CYCLES_REAL         0
-#define VMI_CYCLES_AVAILABLE    1
-#define VMI_CYCLES_STOLEN       2
-
-/* The alarm interface 'flags' bits */
-#define VMI_ALARM_COUNTERS      2
-
-#define VMI_ALARM_COUNTER_MASK  0x000000ff
-
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-
-#define VMI_ALARM_IS_ONESHOT    0x00000000
-#define VMI_ALARM_IS_PERIODIC   0x00000100
-
-#define CONFIG_VMI_ALARM_HZ     100
-
-#endif /* _ASM_X86_VMI_TIME_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9f0cbd987d50..84471b810460 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -66,15 +66,23 @@
 #define PIN_BASED_NMI_EXITING                   0x00000008
 #define PIN_BASED_VIRTUAL_NMIS                  0x00000020
 
+#define VM_EXIT_SAVE_DEBUG_CONTROLS             0x00000002
 #define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL      0x00001000
 #define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
 #define VM_EXIT_SAVE_IA32_PAT                   0x00040000
 #define VM_EXIT_LOAD_IA32_PAT                   0x00080000
+#define VM_EXIT_SAVE_IA32_EFER                  0x00100000
+#define VM_EXIT_LOAD_IA32_EFER                  0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER       0x00400000
 
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS            0x00000002
 #define VM_ENTRY_IA32E_MODE                     0x00000200
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL     0x00002000
 #define VM_ENTRY_LOAD_IA32_PAT                  0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER                 0x00008000
 
 /* VMCS Encodings */
 enum vmcs_field {
@@ -239,6 +247,7 @@ enum vmcs_field {
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
 #define EXIT_REASON_HLT                 12
+#define EXIT_REASON_INVD                13
 #define EXIT_REASON_INVLPG              14
 #define EXIT_REASON_RDPMC               15
 #define EXIT_REASON_RDTSC               16
@@ -296,6 +305,12 @@ enum vmcs_field {
 #define GUEST_INTR_STATE_SMI            0x00000004
 #define GUEST_INTR_STATE_NMI            0x00000008
 
+/* GUEST_ACTIVITY_STATE flags */
+#define GUEST_ACTIVITY_ACTIVE           0
+#define GUEST_ACTIVITY_HLT              1
+#define GUEST_ACTIVITY_SHUTDOWN         2
+#define GUEST_ACTIVITY_WAIT_SIPI        3
+
 /*
  * Exit Qualifications for MOV for Control Register Access
  */
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d0983d255fbd..d55597351f6a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -16,27 +16,19 @@ enum vsyscall_num {
 #ifdef __KERNEL__
 #include <linux/seqlock.h>
 
-#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16)))
-#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
-
 /* Definitions for CONFIG_GENERIC_TIME definitions */
-#define __section_vsyscall_gtod_data __attribute__ \
-        ((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
-#define __section_vsyscall_clock __attribute__ \
-        ((unused, __section__ (".vsyscall_clock"),aligned(16)))
 #define __vsyscall_fn \
         __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
 
 #define VGETCPU_RDTSCP  1
 #define VGETCPU_LSL     2
 
-extern int __vgetcpu_mode;
-extern volatile unsigned long __jiffies;
-
 /* kernel space (writeable) */
 extern int vgetcpu_mode;
 extern struct timezone sys_tz;
 
+#include <asm/vvar.h>
+
 extern void map_vsyscall(void);
 
 #endif /* __KERNEL__ */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
new file mode 100644
index 000000000000..341b3559452b
--- /dev/null
+++ b/arch/x86/include/asm/vvar.h
@@ -0,0 +1,52 @@
+/*
+ * vvar.h: Shared vDSO/kernel variable declarations
+ * Copyright (c) 2011 Andy Lutomirski
+ * Subject to the GNU General Public License, version 2
+ *
+ * A handful of variables are accessible (read-only) from userspace
+ * code in the vsyscall page and the vdso.  They are declared here.
+ * Some other file must define them with DEFINE_VVAR.
+ *
+ * In normal kernel code, they are used like any other variable.
+ * In user code, they are accessed through the VVAR macro.
+ *
+ * Each of these variables lives in the vsyscall page, and each
+ * one needs a unique offset within the little piece of the page
+ * reserved for vvars.  Specify that offset in DECLARE_VVAR.
+ * (There are 896 bytes available.  If you mess up, the linker will
+ * catch it.)
+ */
+
+/* Offset of vars within vsyscall page */
+#define VSYSCALL_VARS_OFFSET (3072 + 128)
+
+#if defined(__VVAR_KERNEL_LDS)
+
+/* The kernel linker script defines its own magic to put vvars in the
+ * right place.
+ */
+#define DECLARE_VVAR(offset, type, name) \
+        EMIT_VVAR(name, VSYSCALL_VARS_OFFSET + offset)
+
+#else
+
+#define DECLARE_VVAR(offset, type, name)                                \
+        static type const * const vvaraddr_ ## name =                   \
+                (void *)(VSYSCALL_START + VSYSCALL_VARS_OFFSET + (offset));
+
+#define DEFINE_VVAR(type, name)                                         \
+        type __vvar_ ## name                                            \
+        __attribute__((section(".vsyscall_var_" #name), aligned(16)))
+
+#define VVAR(name) (*vvaraddr_ ## name)
+
+#endif
+
+/* DECLARE_VVAR(offset, type, name) */
+
+DECLARE_VVAR(0, volatile unsigned long, jiffies)
+DECLARE_VVAR(8, int, vgetcpu_mode)
+DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
+
+#undef DECLARE_VVAR
+#undef VSYSCALL_VARS_OFFSET
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
new file mode 100644
index 000000000000..6bf5b8e478c0
--- /dev/null
+++ b/arch/x86/include/asm/x2apic.h
@@ -0,0 +1,62 @@
+/*
+ * Common bits for X2APIC cluster/physical modes.
+ */
+
+#ifndef _ASM_X86_X2APIC_H
+#define _ASM_X86_X2APIC_H
+
+#include <asm/apic.h>
+#include <asm/ipi.h>
+#include <linux/cpumask.h>
+
+/*
+ * Need to use more than cpu 0, because we need more vectors
+ * when MSI-X are used.
+ */
+static const struct cpumask *x2apic_target_cpus(void)
+{
+        return cpu_online_mask;
+}
+
+static int x2apic_apic_id_registered(void)
+{
+        return 1;
+}
+
+/*
+ * For now each logical cpu is in its own vector allocation domain.
+ */
+static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
+{
+        cpumask_clear(retmask);
+        cpumask_set_cpu(cpu, retmask);
+}
+
+static void
+__x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
+{
+        unsigned long cfg = __prepare_ICR(0, vector, dest);
+        native_x2apic_icr_write(cfg, apicid);
+}
+
+static unsigned int x2apic_get_apic_id(unsigned long id)
+{
+        return id;
+}
+
+static unsigned long x2apic_set_apic_id(unsigned int id)
+{
+        return id;
+}
+
+static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
+{
+        return initial_apicid >> index_msb;
+}
+
+static void x2apic_send_IPI_self(int vector)
+{
+        apic_write(APIC_SELF_IPI, vector);
+}
+
+#endif /* _ASM_X86_X2APIC_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index baa579c8e038..d3d859035af9 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -68,6 +68,17 @@ struct x86_init_oem {
 };
 
 /**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve:  reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+        void (*pagetable_reserve)(u64 start, u64 end);
+};
+
+/**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_setup_start:      platform specific pre paging_init() call
  * @pagetable_setup_done:       platform specific post paging_init() call
@@ -83,11 +94,13 @@ struct x86_init_paging {
  *                              boot cpu
  * @tsc_pre_init:               platform function called before TSC init
  * @timer_init:                 initialize the platform timer (default PIT/HPET)
+ * @wallclock_init:             init the wallclock device
  */
 struct x86_init_timers {
         void (*setup_percpu_clockev)(void);
         void (*tsc_pre_init)(void);
         void (*timer_init)(void);
+        void (*wallclock_init)(void);
 };
 
 /**
@@ -121,6 +134,7 @@ struct x86_init_ops {
         struct x86_init_mpparse         mpparse;
         struct x86_init_irqs            irqs;
         struct x86_init_oem             oem;
+        struct x86_init_mapping         mapping;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
         struct x86_init_iommu           iommu;
@@ -154,9 +168,18 @@ struct x86_platform_ops {
         int (*i8042_detect)(void);
 };
 
+struct pci_dev;
+
+struct x86_msi_ops {
+        int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+        void (*teardown_msi_irq)(unsigned int irq);
+        void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
 extern struct x86_init_ops x86_init;
 extern struct x86_cpuinit_ops x86_cpuinit;
 extern struct x86_platform_ops x86_platform;
+extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7fda040a76cd..d240ea950519 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -200,6 +200,23 @@ extern struct { char _entry[32]; } hypercall_page[];
         (type)__res;                                                    \
 })
 
+static inline long
+privcmd_call(unsigned call,
+             unsigned long a1, unsigned long a2,
+             unsigned long a3, unsigned long a4,
+             unsigned long a5)
+{
+        __HYPERCALL_DECLS;
+        __HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+
+        asm volatile("call *%[call]"
+                     : __HYPERCALL_5PARAM
+                     : [call] "a" (&hypercall_page[call])
+                     : __HYPERCALL_CLOBBER5);
+
+        return (long)__res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
@@ -270,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
-        return _hypercall2(int, sched_op_new, cmd, arg);
+        return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
@@ -405,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value)
 #endif
 
 static inline int
-HYPERVISOR_suspend(unsigned long srec)
+HYPERVISOR_suspend(unsigned long start_info_mfn)
 {
-        return _hypercall3(int, sched_op, SCHEDOP_shutdown,
-                           SHUTDOWN_suspend, srec);
+        struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+        /*
+         * For a PV guest the tools require that the start_info mfn be
+         * present in rdx/edx when the hypercall is made. Per the
+         * hypercall calling convention this is the third hypercall
+         * argument, which is start_info_mfn here.
+         */
+        return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
 }
 
 static inline int
@@ -423,6 +447,13 @@ HYPERVISOR_hvm_op(int op, void *arg)
        return _hypercall2(unsigned long, hvm_op, op, arg);
 }
 
+static inline int
+HYPERVISOR_tmem_op(
+        struct tmem_op *op)
+{
+        return _hypercall1(int, tmem_op, op);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
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/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index e8506c1f0c55..5d4922ad4b9b 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void);
 #define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
 #endif
 
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
 
 /* Maximum number of virtual CPUs in multi-processor guests. */
 #define MAX_VIRT_CPUS 32
@@ -86,7 +86,7 @@ DEFINE_GUEST_HANDLE(void);
  * The privilege level specifies which modes may enter a trap via a software
  * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
  * privilege levels as follows:
- *  Level == 0: Noone may enter
+ *  Level == 0: No one may enter
  *  Level == 1: Kernel may enter
  *  Level == 2: Kernel may enter
  *  Level == 3: Everyone may enter
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index 42a7e004ae5c..8413688b2571 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -32,6 +32,11 @@
 /* And the trap vector is... */
 #define TRAP_INSTR "int $0x82"
 
+#define __MACH2PHYS_VIRT_START 0xF5800000
+#define __MACH2PHYS_VIRT_END   0xF6800000
+
+#define __MACH2PHYS_SHIFT      2
+
 /*
  * Virtual addresses beyond this are not modifiable by guest OSes. The
  * machine->physical mapping table starts at this address, read-only.
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index 100d2662b97c..839a4811cf98 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -39,18 +39,7 @@
 #define __HYPERVISOR_VIRT_END   0xFFFF880000000000
 #define __MACH2PHYS_VIRT_START  0xFFFF800000000000
 #define __MACH2PHYS_VIRT_END    0xFFFF804000000000
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
-#endif
-
-#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define __MACH2PHYS_SHIFT       3
 
 /*
  * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index bf5f7d32bd08..64a619d47d34 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/pfn.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -28,23 +29,46 @@ typedef struct xpaddr {
 
 /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
 #define INVALID_P2M_ENTRY       (~0UL)
-#define FOREIGN_FRAME_BIT       (1UL<<31)
+#define FOREIGN_FRAME_BIT       (1UL<<(BITS_PER_LONG-1))
+#define IDENTITY_FRAME_BIT      (1UL<<(BITS_PER_LONG-2))
 #define FOREIGN_FRAME(m)        ((m) | FOREIGN_FRAME_BIT)
+#define IDENTITY_FRAME(m)       ((m) | IDENTITY_FRAME_BIT)
 
 /* Maximum amount of memory we can handle in a domain in pages */
 #define MAX_DOMAIN_PAGES                                                \
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
+extern unsigned long *machine_to_phys_mapping;
+extern unsigned int   machine_to_phys_order;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
-extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-
+extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern unsigned long set_phys_range_identity(unsigned long pfn_s,
+                                             unsigned long pfn_e);
+
+extern int m2p_add_override(unsigned long mfn, struct page *page,
+                            bool clear_pte);
+extern int m2p_remove_override(struct page *page, bool clear_pte);
+extern struct page *m2p_find_override(unsigned long mfn);
+extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+extern int p2m_dump_show(struct seq_file *m, void *v);
+#endif
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
+        unsigned long mfn;
+
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return pfn;
 
-        return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
+        mfn = get_phys_to_machine(pfn);
+
+        if (mfn != INVALID_P2M_ENTRY)
+                mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
+
+        return mfn;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -58,22 +82,44 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
 {
         unsigned long pfn;
+        int ret = 0;
 
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return mfn;
 
-#if 0
-        if (unlikely((mfn >> machine_to_phys_order) != 0))
-                return max_mapnr;
-#endif
-
+        if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+                pfn = ~0;
+                goto try_override;
+        }
         pfn = 0;
         /*
          * The array access can fail (e.g., device space beyond end of RAM).
          * In such cases it doesn't matter what we return (we return garbage),
          * but we must handle the fault without crashing!
          */
-        __get_user(pfn, &machine_to_phys_mapping[mfn]);
+        ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+try_override:
+        /* ret might be < 0 if there are no entries in the m2p for mfn */
+        if (ret < 0)
+                pfn = ~0;
+        else if (get_phys_to_machine(pfn) != mfn)
+                /*
+                 * If this appears to be a foreign mfn (because the pfn
+                 * doesn't map back to the mfn), then check the local override
+                 * table to see if there's a better pfn to use.
+                 *
+                 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
+                 */
+                pfn = m2p_find_override_pfn(mfn, ~0);
+
+        /* 
+         * pfn is ~0 if there are no entries in the m2p for mfn or if the
+         * entry doesn't map back to the mfn and m2p_override doesn't have a
+         * valid entry for it.
+         */
+        if (pfn == ~0 &&
+                        get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+                pfn = mfn;
 
         return pfn;
 }
@@ -159,6 +205,7 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pgd_val_ma(x)   ((x).pgd)
 
+void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 
 xmaddr_t arbitrary_virt_to_machine(void *address);
 unsigned long arbitrary_virt_to_mfn(void *vaddr);
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
new file mode 100644
index 000000000000..4fbda9a3f339
--- /dev/null
+++ b/arch/x86/include/asm/xen/pci.h
@@ -0,0 +1,81 @@
+#ifndef _ASM_X86_XEN_PCI_H
+#define _ASM_X86_XEN_PCI_H
+
+#if defined(CONFIG_PCI_XEN)
+extern int __init pci_xen_init(void);
+extern int __init pci_xen_hvm_init(void);
+#define pci_xen 1
+#else
+#define pci_xen 0
+#define pci_xen_init (0)
+static inline int pci_xen_hvm_init(void)
+{
+        return -1;
+}
+#endif
+#if defined(CONFIG_XEN_DOM0)
+void __init xen_setup_pirqs(void);
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
+#else
+static inline void __init xen_setup_pirqs(void)
+{
+}
+static inline int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
+static inline int xen_register_device_domain_owner(struct pci_dev *dev,
+                                                   uint16_t domain)
+{
+        return -1;
+}
+static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
+#endif
+
+#if defined(CONFIG_PCI_MSI)
+#if defined(CONFIG_PCI_XEN)
+/* The drivers/pci/xen-pcifront.c sets this structure to
+ * its own functions.
+ */
+struct xen_pci_frontend_ops {
+        int (*enable_msi)(struct pci_dev *dev, int vectors[]);
+        void (*disable_msi)(struct pci_dev *dev);
+        int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec);
+        void (*disable_msix)(struct pci_dev *dev);
+};
+
+extern struct xen_pci_frontend_ops *xen_pci_frontend;
+
+static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
+                                              int vectors[])
+{
+        if (xen_pci_frontend && xen_pci_frontend->enable_msi)
+                return xen_pci_frontend->enable_msi(dev, vectors);
+        return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
+{
+        if (xen_pci_frontend && xen_pci_frontend->disable_msi)
+                        xen_pci_frontend->disable_msi(dev);
+}
+static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
+                                               int vectors[], int nvec)
+{
+        if (xen_pci_frontend && xen_pci_frontend->enable_msix)
+                return xen_pci_frontend->enable_msix(dev, vectors, nvec);
+        return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
+{
+        if (xen_pci_frontend && xen_pci_frontend->disable_msix)
+                        xen_pci_frontend->disable_msix(dev);
+}
+#endif /* CONFIG_PCI_XEN */
+#endif /* CONFIG_PCI_MSI */
+
+#endif  /* _ASM_X86_XEN_PCI_H */