27 files changed, 290 insertions, 125 deletions

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 13009d1af99a..bf535f947e8c 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -4,7 +4,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
-#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -191,12 +190,4 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-#define IDEAL_NOP_SIZE_5 5
-extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
-extern void arch_init_ideal_nop5(void);
-#else
-static inline void arch_init_ideal_nop5(void) {}
-#endif
-
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index 916bc8111a01..55d95eb789b3 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -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 e3509fc303bf..4c9982995414 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -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
@@ -409,9 +432,6 @@ 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;
 
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index d87988bacf3e..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
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 91f3e087cf21..7f2f7b123293 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -195,6 +195,7 @@
 
 /* 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_ERMS        (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8e4a16508d4e..7093e4a6a0bc 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,6 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+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/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/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/io_apic.h b/arch/x86/include/asm/io_apic.h
index c4bd267dfc50..a97a240f67f3 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -150,7 +150,7 @@ void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
-int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 574dbc22893a..a32b18ce6ead 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -5,20 +5,25 @@
 
 #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"
-
-# define JUMP_LABEL(key, label)                                 \
-        do {                                                    \
-                asm goto("1:"                                   \
-                        JUMP_LABEL_INITIAL_NOP                  \
-                        ".pushsection __jump_table,  \"aw\" \n\t"\
-                        _ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
-                        ".popsection \n\t"                      \
-                        : :  "i" (key) :  : label);             \
-        } while (0)
+#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__ */
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index eb16e94ae04f..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);
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 67763c5d8b4e..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 "
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index af788496020b..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
@@ -29,13 +36,14 @@
    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 (arbitrary choice)
@@ -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 3d4dab43c994..a50fc9f493b3 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -51,7 +51,7 @@ static inline void numa_remove_cpu(int cpu)		{ }
 #endif  /* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #endif
 
 #endif  /* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d475b4398d8b..751e7f3f705c 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -517,7 +517,7 @@ do {									\
         typeof(o2) __o2 = o2;                                           \
         typeof(o2) __n2 = n2;                                           \
         typeof(o2) __dummy;                                             \
-        alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4,      \
+        alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4,     \
                        "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",  \
                        X86_FEATURE_CX16,                                \
                        ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),         \
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7db7723d1f32..d56187c6b838 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -299,6 +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/setup.h b/arch/x86/include/asm/setup.h
index db8aa19a08a2..647d8a06ce4f 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -88,7 +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;" \
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index d7e89c83645d..70bbe39043a9 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -37,9 +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);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 12569e691ce3..c2ff2a1d845e 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -303,24 +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/uaccess.h b/arch/x86/include/asm/uaccess.h
index abd3e0ea762a..99f0ad753f32 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -42,7 +42,7 @@
  * 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/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 3e094af443c3..130f1eeee5fe 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -94,6 +94,8 @@
 /* after this # consecutive successes, bump up the throttle if it was lowered */
 #define COMPLETE_THRESHOLD 5
 
+#define UV_LB_SUBNODEID 0x10
+
 /*
  * number of entries in the destination side payload queue
  */
@@ -124,7 +126,7 @@
  * 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 {
@@ -176,7 +178,7 @@ struct bau_msg_payload {
 struct bau_msg_header {
         unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
         /* bits 5:0 */
-        unsigned int base_dest_nodeid:15; /* nasid of the */
+        unsigned int base_dest_nasid:15; /* nasid of the */
         /* bits 20:6 */                   /* first bit in uvhub map */
         unsigned int command:8; /* message type */
         /* bits 28:21 */
@@ -378,6 +380,10 @@ struct ptc_stats {
         unsigned long d_rcanceled; /* number of messages canceled by resets */
 };
 
+struct hub_and_pnode {
+        short uvhub;
+        short pnode;
+};
 /*
  * one per-cpu; to locate the software tables
  */
@@ -399,10 +405,12 @@ struct bau_control {
         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];
@@ -422,15 +430,16 @@ struct bau_control {
         int congested_period;
         cycles_t period_time;
         long period_requests;
+        struct hub_and_pnode *target_hub_and_pnode;
 };
 
 static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *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_target_uvhubmask *dstp)
 {
-        __set_bit(uvhub, &dstp->bits[0]);
+        __set_bit(pnode, &dstp->bits[0]);
 }
 static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
                                     int nbits)
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index a501741c2335..4298002d0c83 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -398,6 +398,8 @@ 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;
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 20cafeac7455..f5bb64a823d7 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,7 +5,7 @@
  *
  * SGI UV MMR definitions
  *
- * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_MMRS_H
@@ -1099,5 +1099,19 @@ union uvh_rtc1_int_config_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                               UVH_SCRATCH5                                */
+/* ========================================================================= */
+#define UVH_SCRATCH5 0x2d0200UL
+#define UVH_SCRATCH5_32 0x00778
+
+#define UVH_SCRATCH5_SCRATCH5_SHFT 0
+#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+union uvh_scratch5_u {
+    unsigned long       v;
+    struct uvh_scratch5_s {
+        unsigned long   scratch5 : 64;  /* RW, W1CS */
+    } s;
+};
 
 #endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 643ebf2e2ad8..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
@@ -123,6 +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;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c61934fbf22a..64a619d47d34 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -47,8 +47,9 @@ 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);
-extern int m2p_remove_override(struct page *page);
+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);
 
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index aa8620989162..4fbda9a3f339 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -15,10 +15,26 @@ static inline int pci_xen_hvm_init(void)
 #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)