127 files changed, 1282 insertions, 913 deletions

diff --git a/include/asm-alpha/core_mcpcia.h b/include/asm-alpha/core_mcpcia.h
index 525b4f6a7ace..acf55b483472 100644
--- a/include/asm-alpha/core_mcpcia.h
+++ b/include/asm-alpha/core_mcpcia.h
@@ -261,7 +261,7 @@ struct el_MCPCIA_uncorrected_frame_mcheck {
         }
 #endif
 
-static inline int __mcpcia_is_mmio(unsigned long addr)
+extern inline int __mcpcia_is_mmio(unsigned long addr)
 {
         return (addr & 0x80000000UL) == 0;
 }
diff --git a/include/asm-alpha/core_t2.h b/include/asm-alpha/core_t2.h
index 90e6b5d6c214..46bfff58f670 100644
--- a/include/asm-alpha/core_t2.h
+++ b/include/asm-alpha/core_t2.h
@@ -356,13 +356,13 @@ struct el_t2_frame_corrected {
 #define vip     volatile int *
 #define vuip    volatile unsigned int *
 
-static inline u8 t2_inb(unsigned long addr)
+extern inline u8 t2_inb(unsigned long addr)
 {
         long result = *(vip) ((addr << 5) + T2_IO + 0x00);
         return __kernel_extbl(result, addr & 3);
 }
 
-static inline void t2_outb(u8 b, unsigned long addr)
+extern inline void t2_outb(u8 b, unsigned long addr)
 {
         unsigned long w;
 
@@ -371,13 +371,13 @@ static inline void t2_outb(u8 b, unsigned long addr)
         mb();
 }
 
-static inline u16 t2_inw(unsigned long addr)
+extern inline u16 t2_inw(unsigned long addr)
 {
         long result = *(vip) ((addr << 5) + T2_IO + 0x08);
         return __kernel_extwl(result, addr & 3);
 }
 
-static inline void t2_outw(u16 b, unsigned long addr)
+extern inline void t2_outw(u16 b, unsigned long addr)
 {
         unsigned long w;
 
@@ -386,12 +386,12 @@ static inline void t2_outw(u16 b, unsigned long addr)
         mb();
 }
 
-static inline u32 t2_inl(unsigned long addr)
+extern inline u32 t2_inl(unsigned long addr)
 {
         return *(vuip) ((addr << 5) + T2_IO + 0x18);
 }
 
-static inline void t2_outl(u32 b, unsigned long addr)
+extern inline void t2_outl(u32 b, unsigned long addr)
 {
         *(vuip) ((addr << 5) + T2_IO + 0x18) = b;
         mb();
@@ -435,7 +435,7 @@ static inline void t2_outl(u32 b, unsigned long addr)
         set_hae(msb); \
 }
 
-static DEFINE_SPINLOCK(t2_hae_lock);
+extern spinlock_t t2_hae_lock;
 
 /*
  * NOTE: take T2_DENSE_MEM off in each readX/writeX routine, since
diff --git a/include/asm-alpha/io.h b/include/asm-alpha/io.h
index 38f18cf18c9d..e971ab000f95 100644
--- a/include/asm-alpha/io.h
+++ b/include/asm-alpha/io.h
@@ -35,7 +35,7 @@
  * register not being up-to-date with respect to the hardware
  * value.
  */
-static inline void __set_hae(unsigned long new_hae)
+extern inline void __set_hae(unsigned long new_hae)
 {
         unsigned long flags;
         local_irq_save(flags);
@@ -49,7 +49,7 @@ static inline void __set_hae(unsigned long new_hae)
         local_irq_restore(flags);
 }
 
-static inline void set_hae(unsigned long new_hae)
+extern inline void set_hae(unsigned long new_hae)
 {
         if (new_hae != alpha_mv.hae_cache)
                 __set_hae(new_hae);
@@ -176,7 +176,7 @@ REMAP2(u64, writeq, volatile)
 #undef REMAP1
 #undef REMAP2
 
-static inline void __iomem *generic_ioportmap(unsigned long a)
+extern inline void __iomem *generic_ioportmap(unsigned long a)
 {
         return alpha_mv.mv_ioportmap(a);
 }
diff --git a/include/asm-alpha/mmu_context.h b/include/asm-alpha/mmu_context.h
index 6a5be1f7debf..86c08a02d239 100644
--- a/include/asm-alpha/mmu_context.h
+++ b/include/asm-alpha/mmu_context.h
@@ -23,7 +23,7 @@
 #endif
 
 
-extern inline unsigned long
+static inline unsigned long
 __reload_thread(struct pcb_struct *pcb)
 {
         register unsigned long a0 __asm__("$16");
@@ -114,7 +114,7 @@ extern unsigned long last_asn;
 #define __MMU_EXTERN_INLINE
 #endif
 
-static inline unsigned long
+extern inline unsigned long
 __get_new_mm_context(struct mm_struct *mm, long cpu)
 {
         unsigned long asn = cpu_last_asn(cpu);
@@ -226,7 +226,7 @@ ev4_activate_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm)
 # endif
 #endif
 
-extern inline int
+static inline int
 init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
         int i;
diff --git a/include/asm-alpha/percpu.h b/include/asm-alpha/percpu.h
index 48348fe34c19..3495e8e00d70 100644
--- a/include/asm-alpha/percpu.h
+++ b/include/asm-alpha/percpu.h
@@ -1,6 +1,78 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
+#include <linux/compiler.h>
+#include <linux/threads.h>
 
-#include <asm-generic/percpu.h>
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
+#ifdef CONFIG_SMP
+
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ */
+extern unsigned long __per_cpu_offset[NR_CPUS];
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#ifdef CONFIG_DEBUG_PREEMPT
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+#ifndef MODULE
+#define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
+#define PER_CPU_ATTRIBUTES
+#else
+/*
+ * To calculate addresses of locally defined variables, GCC uses 32-bit
+ * displacement from the GP. Which doesn't work for per cpu variables in
+ * modules, as an offset to the kernel per cpu area is way above 4G.
+ *
+ * This forces allocation of a GOT entry for per cpu variable using
+ * ldq instruction with a 'literal' relocation.
+ */
+#define SHIFT_PERCPU_PTR(var, offset) ({                \
+        extern int simple_identifier_##var(void);       \
+        unsigned long __ptr, tmp_gp;                    \
+        asm (  "br      %1, 1f                        \n\
+        1:      ldgp    %1, 0(%1)                     \n\
+                ldq %0, per_cpu__" #var"(%1)\t!literal"         \
+                : "=&r"(__ptr), "=&r"(tmp_gp));         \
+        (typeof(&per_cpu_var(var)))(__ptr + (offset)); })
+
+#define PER_CPU_ATTRIBUTES      __used
+
+#endif /* MODULE */
+
+/*
+ * A percpu variable may point to a discarded regions. The following are
+ * established ways to produce a usable pointer from the percpu variable
+ * offset.
+ */
+#define per_cpu(var, cpu) \
+        (*SHIFT_PERCPU_PTR(var, per_cpu_offset(cpu)))
+#define __get_cpu_var(var) \
+        (*SHIFT_PERCPU_PTR(var, my_cpu_offset))
+#define __raw_get_cpu_var(var) \
+        (*SHIFT_PERCPU_PTR(var, __my_cpu_offset))
+
+#else /* ! SMP */
+
+#define per_cpu(var, cpu)               (*((void)(cpu), &per_cpu_var(var)))
+#define __get_cpu_var(var)              per_cpu_var(var)
+#define __raw_get_cpu_var(var)          per_cpu_var(var)
+
+#define PER_CPU_ATTRIBUTES
+
+#endif /* SMP */
+
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu_var(name)
 
 #endif /* __ALPHA_PERCPU_H */
diff --git a/include/asm-alpha/system.h b/include/asm-alpha/system.h
index ed221d6408fc..afe20fa58c99 100644
--- a/include/asm-alpha/system.h
+++ b/include/asm-alpha/system.h
@@ -184,7 +184,7 @@ enum amask_enum {
    __amask; })
 
 #define __CALL_PAL_R0(NAME, TYPE)                               \
-static inline TYPE NAME(void)                                   \
+extern inline TYPE NAME(void)                                   \
 {                                                               \
         register TYPE __r0 __asm__("$0");                       \
         __asm__ __volatile__(                                   \
@@ -196,7 +196,7 @@ static inline TYPE NAME(void)					\
 }
 
 #define __CALL_PAL_W1(NAME, TYPE0)                              \
-static inline void NAME(TYPE0 arg0)                             \
+extern inline void NAME(TYPE0 arg0)                             \
 {                                                               \
         register TYPE0 __r16 __asm__("$16") = arg0;             \
         __asm__ __volatile__(                                   \
@@ -207,7 +207,7 @@ static inline void NAME(TYPE0 arg0)				\
 }
 
 #define __CALL_PAL_W2(NAME, TYPE0, TYPE1)                       \
-static inline void NAME(TYPE0 arg0, TYPE1 arg1)                 \
+extern inline void NAME(TYPE0 arg0, TYPE1 arg1)                 \
 {                                                               \
         register TYPE0 __r16 __asm__("$16") = arg0;             \
         register TYPE1 __r17 __asm__("$17") = arg1;             \
@@ -219,7 +219,7 @@ static inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
 }
 
 #define __CALL_PAL_RW1(NAME, RTYPE, TYPE0)                      \
-static inline RTYPE NAME(TYPE0 arg0)                            \
+extern inline RTYPE NAME(TYPE0 arg0)                            \
 {                                                               \
         register RTYPE __r0 __asm__("$0");                      \
         register TYPE0 __r16 __asm__("$16") = arg0;             \
@@ -232,7 +232,7 @@ static inline RTYPE NAME(TYPE0 arg0)				\
 }
 
 #define __CALL_PAL_RW2(NAME, RTYPE, TYPE0, TYPE1)               \
-static inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)                \
+extern inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)                \
 {                                                               \
         register RTYPE __r0 __asm__("$0");                      \
         register TYPE0 __r16 __asm__("$16") = arg0;             \
diff --git a/include/asm-alpha/vga.h b/include/asm-alpha/vga.h
index e8df1e7aae6b..c00106bac521 100644
--- a/include/asm-alpha/vga.h
+++ b/include/asm-alpha/vga.h
@@ -13,7 +13,7 @@
 #define VT_BUF_HAVE_MEMSETW
 #define VT_BUF_HAVE_MEMCPYW
 
-extern inline void scr_writew(u16 val, volatile u16 *addr)
+static inline void scr_writew(u16 val, volatile u16 *addr)
 {
         if (__is_ioaddr(addr))
                 __raw_writew(val, (volatile u16 __iomem *) addr);
@@ -21,7 +21,7 @@ extern inline void scr_writew(u16 val, volatile u16 *addr)
                 *addr = val;
 }
 
-extern inline u16 scr_readw(volatile const u16 *addr)
+static inline u16 scr_readw(volatile const u16 *addr)
 {
         if (__is_ioaddr(addr))
                 return __raw_readw((volatile const u16 __iomem *) addr);
@@ -29,7 +29,7 @@ extern inline u16 scr_readw(volatile const u16 *addr)
                 return *addr;
 }
 
-extern inline void scr_memsetw(u16 *s, u16 c, unsigned int count)
+static inline void scr_memsetw(u16 *s, u16 c, unsigned int count)
 {
         if (__is_ioaddr(s))
                 memsetw_io((u16 __iomem *) s, c, count);
diff --git a/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h
index 96bd09e31e36..2526b6ed6faa 100644
--- a/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h
+++ b/include/asm-blackfin/mach-bf527/bfin_serial_5xx.h
@@ -96,7 +96,7 @@ struct bfin_serial_port {
         struct work_struct tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        struct work_struct cts_workqueue;
+        struct timer_list cts_timer;
         int cts_pin;
         int rts_pin;
 #endif
diff --git a/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h
index e924569ad1d8..ebf592b59aab 100644
--- a/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h
+++ b/include/asm-blackfin/mach-bf533/bfin_serial_5xx.h
@@ -88,7 +88,7 @@ struct bfin_serial_port {
 # endif
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        struct work_struct      cts_workqueue;
+        struct timer_list       cts_timer;
         int                     cts_pin;
         int                     rts_pin;
 #endif
diff --git a/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h
index 41d7b6490bb1..1bf56ffa22f9 100644
--- a/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h
+++ b/include/asm-blackfin/mach-bf537/bfin_serial_5xx.h
@@ -96,7 +96,7 @@ struct bfin_serial_port {
         struct work_struct      tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        struct work_struct      cts_workqueue;
+        struct timer_list       cts_timer;
         int             cts_pin;
         int             rts_pin;
 #endif
diff --git a/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h
index 59b4ad4e5b4a..5e29446a8e03 100644
--- a/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h
+++ b/include/asm-blackfin/mach-bf548/bfin_serial_5xx.h
@@ -99,7 +99,7 @@ struct bfin_serial_port {
         struct work_struct      tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        struct work_struct      cts_workqueue;
+        struct timer_list       cts_timer;
         int             cts_pin;
         int             rts_pin;
 #endif
@@ -187,7 +187,7 @@ static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 
 #ifdef CONFIG_BFIN_UART1_CTSRTS
         peripheral_request(P_UART1_RTS, DRIVER_NAME);
-        peripheral_request(P_UART1_CTS DRIVER_NAME);
+        peripheral_request(P_UART1_CTS, DRIVER_NAME);
 #endif
 #endif
 
@@ -202,7 +202,7 @@ static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 
 #ifdef CONFIG_BFIN_UART3_CTSRTS
         peripheral_request(P_UART3_RTS, DRIVER_NAME);
-        peripheral_request(P_UART3_CTS DRIVER_NAME);
+        peripheral_request(P_UART3_CTS, DRIVER_NAME);
 #endif
 #endif
         SSYNC();
diff --git a/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h b/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h
index 30d90b580f18..8aa02780e642 100644
--- a/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h
+++ b/include/asm-blackfin/mach-bf561/bfin_serial_5xx.h
@@ -88,7 +88,7 @@ struct bfin_serial_port {
 # endif
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        struct work_struct      cts_workqueue;
+        struct timer_list       cts_timer;
         int                     cts_pin;
         int                     rts_pin;
 #endif
diff --git a/include/asm-generic/Kbuild.asm b/include/asm-generic/Kbuild.asm
index 92a6d91d0c1a..7cd25b8e7c9a 100644
--- a/include/asm-generic/Kbuild.asm
+++ b/include/asm-generic/Kbuild.asm
@@ -1,6 +1,6 @@
 header-y  += kvm.h
 
-ifeq ($(wildcard include/asm-$(SRCARCH)/a.out.h),include/asm-$(SRCARCH)/a.out.h)
+ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/a.out.h),)
 unifdef-y += a.out.h
 endif
 unifdef-y += auxvec.h
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 85fd0aa27a8c..4ec0a296bdec 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -2,7 +2,7 @@
 #define _ASM_GENERIC_ATOMIC_H
 /*
  * Copyright (C) 2005 Silicon Graphics, Inc.
- *      Christoph Lameter <clameter@sgi.com>
+ *      Christoph Lameter
  *
  * Allows to provide arch independent atomic definitions without the need to
  * edit all arch specific atomic.h files.
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 44ef329531c3..4fce3db2cecc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -197,6 +197,63 @@ static inline int pmd_none_or_clear_bad(pmd_t *pmd)
 }
 #endif /* CONFIG_MMU */
 
+static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
+                                             unsigned long addr,
+                                             pte_t *ptep)
+{
+        /*
+         * Get the current pte state, but zero it out to make it
+         * non-present, preventing the hardware from asynchronously
+         * updating it.
+         */
+        return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
+                                             unsigned long addr,
+                                             pte_t *ptep, pte_t pte)
+{
+        /*
+         * The pte is non-present, so there's no hardware state to
+         * preserve.
+         */
+        set_pte_at(mm, addr, ptep, pte);
+}
+
+#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+/*
+ * Start a pte protection read-modify-write transaction, which
+ * protects against asynchronous hardware modifications to the pte.
+ * The intention is not to prevent the hardware from making pte
+ * updates, but to prevent any updates it may make from being lost.
+ *
+ * This does not protect against other software modifications of the
+ * pte; the appropriate pte lock must be held over the transation.
+ *
+ * Note that this interface is intended to be batchable, meaning that
+ * ptep_modify_prot_commit may not actually update the pte, but merely
+ * queue the update to be done at some later time.  The update must be
+ * actually committed before the pte lock is released, however.
+ */
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
+                                           unsigned long addr,
+                                           pte_t *ptep)
+{
+        return __ptep_modify_prot_start(mm, addr, ptep);
+}
+
+/*
+ * Commit an update to a pte, leaving any hardware-controlled bits in
+ * the PTE unmodified.
+ */
+static inline void ptep_modify_prot_commit(struct mm_struct *mm,
+                                           unsigned long addr,
+                                           pte_t *ptep, pte_t pte)
+{
+        __ptep_modify_prot_commit(mm, addr, ptep, pte);
+}
+#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
+
 /*
  * A facility to provide lazy MMU batching.  This allows PTE updates and
  * page invalidations to be delayed until a call to leave lazy MMU mode
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f054778e916c..f1992dc5c424 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -93,6 +93,8 @@
                 VMLINUX_SYMBOL(__end_rio_route_ops) = .;                \
         }                                                               \
                                                                         \
+        TRACEDATA                                                       \
+                                                                        \
         /* Kernel symbol table: Normal symbols */                       \
         __ksymtab         : AT(ADDR(__ksymtab) - LOAD_OFFSET) {         \
                 VMLINUX_SYMBOL(__start___ksymtab) = .;                  \
@@ -318,6 +320,18 @@
                 __stop___bug_table = .;                                 \
         }
 
+#ifdef CONFIG_PM_TRACE
+#define TRACEDATA                                                       \
+        . = ALIGN(4);                                                   \
+        .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {               \
+                __tracedata_start = .;                                  \
+                *(.tracedata)                                           \
+                __tracedata_end = .;                                    \
+        }
+#else
+#define TRACEDATA
+#endif
+
 #define NOTES                                                           \
         .notes : AT(ADDR(.notes) - LOAD_OFFSET) {                       \
                 VMLINUX_SYMBOL(__start_notes) = .;                      \
diff --git a/include/asm-ia64/sn/simulator.h b/include/asm-ia64/sn/simulator.h
index c3fd3eb25768..c2611f6cfe33 100644
--- a/include/asm-ia64/sn/simulator.h
+++ b/include/asm-ia64/sn/simulator.h
@@ -8,7 +8,7 @@
 #ifndef _ASM_IA64_SN_SIMULATOR_H
 #define _ASM_IA64_SN_SIMULATOR_H
 
-
+#if defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_SGI_UV)
 #define SNMAGIC 0xaeeeeeee8badbeefL
 #define IS_MEDUSA()                     ({long sn; asm("mov %0=cpuid[%1]" : "=r"(sn) : "r"(2)); sn == SNMAGIC;})
 
@@ -16,5 +16,10 @@
 #define IS_RUNNING_ON_SIMULATOR()       (sn_prom_type)
 #define IS_RUNNING_ON_FAKE_PROM()       (sn_prom_type == 2)
 extern int sn_prom_type;                /* 0=hardware, 1=medusa/realprom, 2=medusa/fakeprom */
+#else
+#define IS_MEDUSA()                     0
+#define SIMULATOR_SLEEP()
+#define IS_RUNNING_ON_SIMULATOR()       0
+#endif
 
 #endif /* _ASM_IA64_SN_SIMULATOR_H */
diff --git a/include/asm-mips/atomic.h b/include/asm-mips/atomic.h
index a798d6299a79..1232be3885b0 100644
--- a/include/asm-mips/atomic.h
+++ b/include/asm-mips/atomic.h
@@ -283,10 +283,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
                 "       beqz    %0, 2f                                  \n"
                 "        subu   %0, %1, %3                              \n"
                 "       .set    reorder                                 \n"
-                "1:                                                     \n"
                 "       .subsection 2                                   \n"
                 "2:     b       1b                                      \n"
                 "       .previous                                       \n"
+                "1:                                                     \n"
                 "       .set    mips0                                   \n"
                 : "=&r" (result), "=&r" (temp), "=m" (v->counter)
                 : "Ir" (i), "m" (v->counter)
@@ -664,10 +664,10 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
                 "       beqz    %0, 2f                                  \n"
                 "        dsubu  %0, %1, %3                              \n"
                 "       .set    reorder                                 \n"
-                "1:                                                     \n"
                 "       .subsection 2                                   \n"
                 "2:     b       1b                                      \n"
                 "       .previous                                       \n"
+                "1:                                                     \n"
                 "       .set    mips0                                   \n"
                 : "=&r" (result), "=&r" (temp), "=m" (v->counter)
                 : "Ir" (i), "m" (v->counter)
diff --git a/include/asm-mips/cpu-info.h b/include/asm-mips/cpu-info.h
index 0c5a358863f3..2de73dbb2e9e 100644
--- a/include/asm-mips/cpu-info.h
+++ b/include/asm-mips/cpu-info.h
@@ -56,7 +56,7 @@ struct cpuinfo_mips {
         struct cache_desc       tcache; /* Tertiary/split secondary cache */
         int                     srsets; /* Shadow register sets */
         int                     core;   /* physical core number */
-#if defined(CONFIG_MIPS_MT_SMTC)
+#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
         /*
          * In the MIPS MT "SMTC" model, each TC is considered
          * to be a "CPU" for the purposes of scheduling, but
@@ -64,7 +64,7 @@ struct cpuinfo_mips {
          * to all TCs within the same VPE.
          */
         int                     vpe_id;  /* Virtual Processor number */
-#endif /* CONFIG_MIPS_MT */
+#endif
 #ifdef CONFIG_MIPS_MT_SMTC
         int                     tc_id;   /* Thread Context number */
 #endif
diff --git a/include/asm-mips/gic.h b/include/asm-mips/gic.h
index 3a492f225f00..954807d9d66a 100644
--- a/include/asm-mips/gic.h
+++ b/include/asm-mips/gic.h
@@ -24,8 +24,8 @@
 
 #define MSK(n) ((1 << (n)) - 1)
 #define REG32(addr)             (*(volatile unsigned int *) (addr))
-#define REG(base, offs)         REG32((unsigned int)(base) + offs##_##OFS)
-#define REGP(base, phys)        REG32((unsigned int)(base) + (phys))
+#define REG(base, offs)         REG32((unsigned long)(base) + offs##_##OFS)
+#define REGP(base, phys)        REG32((unsigned long)(base) + (phys))
 
 /* Accessors */
 #define GIC_REG(segment, offset) \
diff --git a/include/asm-mips/lasat/serial.h b/include/asm-mips/lasat/serial.h
index bafe68b10614..1c37d70579b8 100644
--- a/include/asm-mips/lasat/serial.h
+++ b/include/asm-mips/lasat/serial.h
@@ -4,10 +4,10 @@
 #define LASAT_BASE_BAUD_100             (7372800 / 16)
 #define LASAT_UART_REGS_BASE_100        0x1c8b0000
 #define LASAT_UART_REGS_SHIFT_100       2
-#define LASATINT_UART_100               8
+#define LASATINT_UART_100               16
 
 /* * LASAT 200 boards serial configuration */
 #define LASAT_BASE_BAUD_200             (100000000 / 16 / 12)
 #define LASAT_UART_REGS_BASE_200        (Vrc5074_PHYS_BASE + 0x0300)
 #define LASAT_UART_REGS_SHIFT_200       3
-#define LASATINT_UART_200               13
+#define LASATINT_UART_200               21
diff --git a/include/asm-mips/mach-au1x00/au1000.h b/include/asm-mips/mach-au1x00/au1000.h
index 1b5064dac007..0d302bad4492 100644
--- a/include/asm-mips/mach-au1x00/au1000.h
+++ b/include/asm-mips/mach-au1x00/au1000.h
@@ -615,6 +615,7 @@ enum soc_au1500_ints {
         AU1000_RTC_MATCH1_INT,
         AU1000_RTC_MATCH2_INT,
         AU1500_PCI_ERR_INT,
+        AU1500_RESERVED_INT,
         AU1000_USB_DEV_REQ_INT,
         AU1000_USB_DEV_SUS_INT,
         AU1000_USB_HOST_INT,
diff --git a/include/asm-mips/pgtable-bits.h b/include/asm-mips/pgtable-bits.h
index 60e2f9338fcd..51b34a48c84a 100644
--- a/include/asm-mips/pgtable-bits.h
+++ b/include/asm-mips/pgtable-bits.h
@@ -134,6 +134,4 @@
 
 #define _PAGE_CHG_MASK  (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED | _CACHE_MASK)
 
-#define CONF_CM_DEFAULT         (PAGE_CACHABLE_DEFAULT>>_CACHE_SHIFT)
-
 #endif /* _ASM_PGTABLE_BITS_H */
diff --git a/include/asm-powerpc/Kbuild b/include/asm-powerpc/Kbuild
index 7381916dfcbb..bca352e033c3 100644
--- a/include/asm-powerpc/Kbuild
+++ b/include/asm-powerpc/Kbuild
@@ -1,6 +1,5 @@
 include include/asm-generic/Kbuild.asm
 
-header-y += a.out.h
 header-y += auxvec.h
 header-y += ioctls.h
 header-y += mman.h
diff --git a/include/asm-powerpc/mediabay.h b/include/asm-powerpc/mediabay.h
index df111c362a7f..b2efb3325808 100644
--- a/include/asm-powerpc/mediabay.h
+++ b/include/asm-powerpc/mediabay.h
@@ -17,8 +17,6 @@
 #define MB_POWER        6       /* media bay contains a Power device (???) */
 #define MB_NO           7       /* media bay contains nothing */
 
-int check_media_bay(struct device_node *which_bay, int what);
-
 /* Number of bays in the machine or 0 */
 extern int media_bay_count;
 
@@ -29,6 +27,16 @@ int check_media_bay_by_base(unsigned long base, int what);
 /* called by IDE PMAC host driver to register IDE controller for media bay */
 int media_bay_set_ide_infos(struct device_node *which_bay, unsigned long base,
                             int irq, ide_hwif_t *hwif);
+
+int check_media_bay(struct device_node *which_bay, int what);
+
+#else
+
+static inline int check_media_bay(struct device_node *which_bay, int what)
+{
+        return -ENODEV;
+}
+
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h
index 6abead6e681a..99348c1f4cab 100644
--- a/include/asm-powerpc/spu.h
+++ b/include/asm-powerpc/spu.h
@@ -131,7 +131,6 @@ struct spu {
         u64 flags;
         u64 class_0_pending;
         u64 class_0_dar;
-        u64 class_0_dsisr;
         u64 class_1_dar;
         u64 class_1_dsisr;
         size_t ls_size;
diff --git a/include/asm-powerpc/spu_csa.h b/include/asm-powerpc/spu_csa.h
index 129ec148d451..a40fd491250c 100644
--- a/include/asm-powerpc/spu_csa.h
+++ b/include/asm-powerpc/spu_csa.h
@@ -254,7 +254,7 @@ struct spu_state {
         u64 spu_chnldata_RW[32];
         u32 spu_mailbox_data[4];
         u32 pu_mailbox_data[1];
-        u64 class_0_dar, class_0_dsisr, class_0_pending;
+        u64 class_0_dar, class_0_pending;
         u64 class_1_dar, class_1_dsisr;
         unsigned long suspend_time;
         spinlock_t register_lock;
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 2b6559a6d113..5235f875b932 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -34,7 +34,7 @@
  * SMP since it is only used to order updates to system memory.
  */
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
-#define rmb()  __asm__ __volatile__ (__stringify(LWSYNC) : : : "memory")
+#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define read_barrier_depends()  do { } while(0)
 
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index be9639a9a186..313bcaf4b6c3 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -36,14 +36,10 @@ extern void generic_apic_probe(void);
 #ifdef CONFIG_X86_LOCAL_APIC
 
 extern int apic_verbosity;
-extern int timer_over_8254;
 extern int local_apic_timer_c2_ok;
-extern int local_apic_timer_disabled;
 
-extern int apic_runs_main_timer;
 extern int ioapic_force;
 extern int disable_apic;
-extern int disable_apic_timer;
 
 /*
  * Basic functions accessing APICs.
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
index 90dec0c23646..70939820c55f 100644
--- a/include/asm-x86/asm.h
+++ b/include/asm-x86/asm.h
@@ -1,33 +1,29 @@
 #ifndef _ASM_X86_ASM_H
 #define _ASM_X86_ASM_H
 
-#ifdef CONFIG_X86_32
-/* 32 bits */
-
-# define _ASM_PTR       " .long "
-# define _ASM_ALIGN     " .balign 4 "
-# define _ASM_MOV_UL    " movl "
-
-# define _ASM_INC       " incl "
-# define _ASM_DEC       " decl "
-# define _ASM_ADD       " addl "
-# define _ASM_SUB       " subl "
-# define _ASM_XADD      " xaddl "
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x)  x
+#else
+# define __ASM_FORM(x)  " " #x " "
+#endif
 
+#ifdef CONFIG_X86_32
+# define __ASM_SEL(a,b) __ASM_FORM(a)
 #else
-/* 64 bits */
+# define __ASM_SEL(a,b) __ASM_FORM(b)
+#endif
 
-# define _ASM_PTR       " .quad "
-# define _ASM_ALIGN     " .balign 8 "
-# define _ASM_MOV_UL    " movq "
+#define __ASM_SIZE(inst)        __ASM_SEL(inst##l, inst##q)
 
-# define _ASM_INC       " incq "
-# define _ASM_DEC       " decq "
-# define _ASM_ADD       " addq "
-# define _ASM_SUB       " subq "
-# define _ASM_XADD      " xaddq "
+#define _ASM_PTR        __ASM_SEL(.long, .quad)
+#define _ASM_ALIGN      __ASM_SEL(.balign 4, .balign 8)
+#define _ASM_MOV_UL     __ASM_SIZE(mov)
 
-#endif /* CONFIG_X86_32 */
+#define _ASM_INC        __ASM_SIZE(inc)
+#define _ASM_DEC        __ASM_SIZE(dec)
+#define _ASM_ADD        __ASM_SIZE(add)
+#define _ASM_SUB        __ASM_SIZE(sub)
+#define _ASM_XADD       __ASM_SIZE(xadd)
 
 /* Exception table entry */
 # define _ASM_EXTABLE(from,to) \
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index 3e0cd7d38335..fe589c153db8 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -11,12 +11,6 @@
  * resource counting etc..
  */
 
-#ifdef CONFIG_SMP
-#define LOCK "lock ; "
-#else
-#define LOCK ""
-#endif
-
 /*
  * Make sure gcc doesn't try to be clever and move things around
  * on us. We need to use _exactly_ the address the user gave us,
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index ee4b3ead6a43..96b1829cea15 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -23,11 +23,21 @@
 #if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
 /* Technically wrong, but this avoids compilation errors on some gcc
    versions. */
-#define ADDR "=m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
 #else
-#define ADDR "+m" (*(volatile long *) addr)
+#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
 #endif
 
+#define ADDR                            BITOP_ADDR(addr)
+
+/*
+ * We do the locked ops that don't return the old value as
+ * a mask operation on a byte.
+ */
+#define IS_IMMEDIATE(nr)                (__builtin_constant_p(nr))
+#define CONST_MASK_ADDR(nr, addr)       BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK(nr)                  (1 << ((nr) & 7))
+
 /**
  * set_bit - Atomically set a bit in memory
  * @nr: the bit to set
@@ -43,9 +53,17 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(int nr, volatile void *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "orb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)CONST_MASK(nr))
+                        : "memory");
+        } else {
+                asm volatile(LOCK_PREFIX "bts %1,%0"
+                        : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+        }
 }
 
 /**
@@ -57,7 +75,7 @@ static inline void set_bit(int nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile void *addr)
+static inline void __set_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -72,9 +90,17 @@ static inline void __set_bit(int nr, volatile void *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile void *addr)
+static inline void clear_bit(int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "btr %1,%0" : ADDR : "Ir" (nr));
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "andb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)~CONST_MASK(nr)));
+        } else {
+                asm volatile(LOCK_PREFIX "btr %1,%0"
+                        : BITOP_ADDR(addr)
+                        : "Ir" (nr));
+        }
 }
 
 /*
@@ -85,13 +111,13 @@ static inline void clear_bit(int nr, volatile void *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
         barrier();
         clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile void *addr)
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -108,7 +134,7 @@ static inline void __clear_bit(int nr, volatile void *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
+static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
 {
         barrier();
         __clear_bit(nr, addr);
@@ -126,7 +152,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile void *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile void *addr)
+static inline void __change_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -140,7 +166,7 @@ static inline void __change_bit(int nr, volatile void *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(int nr, volatile void *addr)
+static inline void change_bit(int nr, volatile unsigned long *addr)
 {
         asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -153,7 +179,7 @@ static inline void change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(int nr, volatile void *addr)
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -170,7 +196,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile void *addr)
+static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
         return test_and_set_bit(nr, addr);
 }
@@ -184,7 +210,7 @@ static inline int test_and_set_bit_lock(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile void *addr)
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -203,7 +229,7 @@ static inline int __test_and_set_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(int nr, volatile void *addr)
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -223,7 +249,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile void *addr)
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -235,7 +261,7 @@ static inline int __test_and_clear_bit(int nr, volatile void *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile void *addr)
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -255,7 +281,7 @@ static inline int __test_and_change_bit(int nr, volatile void *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(int nr, volatile void *addr)
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 {
         int oldbit;
 
@@ -266,13 +292,13 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
         return oldbit;
 }
 
-static inline int constant_test_bit(int nr, const volatile void *addr)
+static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
 {
         return ((1UL << (nr % BITS_PER_LONG)) &
                 (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
 }
 
-static inline int variable_test_bit(int nr, volatile const void *addr)
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
 {
         int oldbit;
 
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 0d609c837a41..78b47e7404eb 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -142,11 +142,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)   clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
         clear_cpu_cap(&boot_cpu_data, bit);     \
-        set_bit(bit, cleared_cpu_caps);         \
+        set_bit(bit, (unsigned long *)cleared_cpu_caps); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
         set_cpu_cap(&boot_cpu_data, bit);       \
-        clear_bit(bit, cleared_cpu_caps);       \
+        clear_bit(bit, (unsigned long *)cleared_cpu_caps);      \
 } while (0)
 
 #define cpu_has_fpu             boot_cpu_has(X86_FEATURE_FPU)
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
index d2526d3f7346..7515c19d4988 100644
--- a/include/asm-x86/current.h
+++ b/include/asm-x86/current.h
@@ -1,5 +1,39 @@
+#ifndef _X86_CURRENT_H
+#define _X86_CURRENT_H
+
 #ifdef CONFIG_X86_32
-# include "current_32.h"
-#else
-# include "current_64.h"
-#endif
+#include <linux/compiler.h>
+#include <asm/percpu.h>
+
+struct task_struct;
+
+DECLARE_PER_CPU(struct task_struct *, current_task);
+static __always_inline struct task_struct *get_current(void)
+{
+        return x86_read_percpu(current_task);
+}
+
+#else /* X86_32 */
+
+#ifndef __ASSEMBLY__
+#include <asm/pda.h>
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+        return read_pda(pcurrent);
+}
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* X86_32 */
+
+#define current get_current()
+
+#endif /* X86_CURRENT_H */
diff --git a/include/asm-x86/current_32.h b/include/asm-x86/current_32.h
deleted file mode 100644
index 5af9bdb97a16..000000000000
--- a/include/asm-x86/current_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _I386_CURRENT_H
-#define _I386_CURRENT_H
-
-#include <linux/compiler.h>
-#include <asm/percpu.h>
-
-struct task_struct;
-
-DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-        return x86_read_percpu(current_task);
-}
-
-#define current get_current()
-
-#endif /* !(_I386_CURRENT_H) */
diff --git a/include/asm-x86/current_64.h b/include/asm-x86/current_64.h
deleted file mode 100644
index 2d368ede2fc1..000000000000
--- a/include/asm-x86/current_64.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _X86_64_CURRENT_H
-#define _X86_64_CURRENT_H
-
-#if !defined(__ASSEMBLY__)
-struct task_struct;
-
-#include <asm/pda.h>
-
-static inline struct task_struct *get_current(void)
-{
-        struct task_struct *t = read_pda(pcurrent);
-        return t;
-}
-
-#define current get_current()
-
-#else
-
-#ifndef ASM_OFFSET_H
-#include <asm/asm-offsets.h>
-#endif
-
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif
-
-#endif /* !(_X86_64_CURRENT_H) */
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 7004251fc66b..5103d0b2c46c 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -24,6 +24,7 @@ struct e820map {
 
 #define ISA_START_ADDRESS       0xa0000
 #define ISA_END_ADDRESS         0x100000
+#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
 
 #define BIOS_BEGIN              0x000a0000
 #define BIOS_END                0x00100000
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index 4b96148e90c1..f0df7ee96816 100644
--- a/include/asm-x86/fixmap_32.h
+++ b/include/asm-x86/fixmap_32.h
@@ -79,10 +79,6 @@ enum fixed_addresses {
         FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
         FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
 #endif
-#ifdef CONFIG_ACPI
-        FIX_ACPI_BEGIN,
-        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PCI_MMCONFIG
         FIX_PCIE_MCFG,
 #endif
@@ -103,6 +99,10 @@ enum fixed_addresses {
                         (__end_of_permanent_fixed_addresses & 511),
         FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1,
         FIX_WP_TEST,
+#ifdef CONFIG_ACPI
+        FIX_ACPI_BEGIN,
+        FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
         FIX_OHCI1394_BASE,
 #endif
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
index 90958ed993fa..eeca2f51fd8f 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -1,16 +1,20 @@
 #ifndef _ASM_X8664_IOMMU_H
 #define _ASM_X8664_IOMMU_H 1
 
+#include <asm/e820.h>
+
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int agp_amd64_init(void);
 #ifdef CONFIG_GART_IOMMU
 extern void gart_iommu_init(void);
 extern void gart_iommu_shutdown(void);
 extern void __init gart_parse_options(char *);
 extern void early_gart_iommu_check(void);
 extern void gart_iommu_hole_init(void);
+extern void set_up_gart_resume(u32, u32);
 extern int fallback_aper_order;
 extern int fallback_aper_force;
 extern int gart_iommu_aperture;
@@ -31,4 +35,63 @@ static inline void gart_iommu_shutdown(void)
 
 #endif
 
+/* PTE bits. */
+#define GPTE_VALID      1
+#define GPTE_COHERENT   2
+
+/* Aperture control register bits. */
+#define GARTEN          (1<<0)
+#define DISGARTCPU      (1<<4)
+#define DISGARTIO       (1<<5)
+
+/* GART cache control register bits. */
+#define INVGART         (1<<0)
+#define GARTPTEERR      (1<<1)
+
+/* K8 On-cpu GART registers */
+#define AMD64_GARTAPERTURECTL   0x90
+#define AMD64_GARTAPERTUREBASE  0x94
+#define AMD64_GARTTABLEBASE     0x98
+#define AMD64_GARTCACHECTL      0x9c
+#define AMD64_GARTEN            (1<<0)
+
+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);
+}
+
+static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
+{
+        if (!aper_base)
+                return 0;
+
+        if (aper_base + aper_size > 0x100000000ULL) {
+                printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
+                return 0;
+        }
+        if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+                printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
+                return 0;
+        }
+        if (aper_size < min_size) {
+                printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+                                 aper_size>>20, min_size>>20);
+                return 0;
+        }
+
+        return 1;
+}
+
 #endif
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
index 6e6458853a36..bb06027fc83e 100644
--- a/include/asm-x86/geode.h
+++ b/include/asm-x86/geode.h
@@ -112,8 +112,8 @@ extern int geode_get_dev_base(unsigned int dev);
 #define VSA_VR_UNLOCK           0xFC53  /* unlock virtual register */
 #define VSA_VR_SIGNATURE        0x0003
 #define VSA_VR_MEM_SIZE         0x0200
-#define VSA_SIG                 0x4132  /* signature is ascii 'VSA2' */
-
+#define AMD_VSA_SIG             0x4132  /* signature is ascii 'VSA2' */
+#define GSW_VSA_SIG             0x534d  /* General Software signature */
 /* GPIO */
 
 #define GPIO_OUTPUT_VAL         0x00
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
index 45d4df3e51e6..2f98df91f1f2 100644
--- a/include/asm-x86/i8259.h
+++ b/include/asm-x86/i8259.h
@@ -55,4 +55,6 @@ static inline void outb_pic(unsigned char value, unsigned int port)
         udelay(2);
 }
 
+extern struct irq_chip i8259A_chip;
+
 #endif  /* __ASM_I8259_H__ */
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index d593e14f0341..dc0f55f2b034 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -11,6 +11,15 @@
  * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
  */
 
+/* I/O Unit Redirection Table */
+#define IO_APIC_REDIR_VECTOR_MASK       0x000FF
+#define IO_APIC_REDIR_DEST_LOGICAL      0x00800
+#define IO_APIC_REDIR_DEST_PHYSICAL     0x00000
+#define IO_APIC_REDIR_SEND_PENDING      (1 << 12)
+#define IO_APIC_REDIR_REMOTE_IRR        (1 << 14)
+#define IO_APIC_REDIR_LEVEL_TRIGGER     (1 << 15)
+#define IO_APIC_REDIR_MASKED            (1 << 16)
+
 /*
  * The structure of the IO-APIC:
  */
@@ -137,6 +146,9 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
+extern int timer_through_8259;
+
 static inline void disable_ioapic_setup(void)
 {
         skip_ioapic_setup = 1;
@@ -162,6 +174,7 @@ extern void ioapic_init_mappings(void);
 
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
+static const int timer_through_8259 = 0;
 #endif
 
 #endif
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index 1d8cd01fa514..844f2a89afbc 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -18,6 +18,7 @@
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
 
+#include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 
 #define KVM_MAX_VCPUS 16
@@ -282,7 +283,8 @@ struct kvm_vcpu_arch {
         struct x86_emulate_ctxt emulate_ctxt;
 
         gpa_t time;
-        struct kvm_vcpu_time_info hv_clock;
+        struct pvclock_vcpu_time_info hv_clock;
+        unsigned int hv_clock_tsc_khz;
         unsigned int time_offset;
         struct page *time_page;
 };
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index 509845942070..76f392146daa 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -48,24 +48,6 @@ struct kvm_mmu_op_release_pt {
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
-/* xen binary-compatible interface. See xen headers for details */
-struct kvm_vcpu_time_info {
-        uint32_t version;
-        uint32_t pad0;
-        uint64_t tsc_timestamp;
-        uint64_t system_time;
-        uint32_t tsc_to_system_mul;
-        int8_t   tsc_shift;
-        int8_t   pad[3];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct kvm_wall_clock {
-        uint32_t wc_version;
-        uint32_t wc_sec;
-        uint32_t wc_nsec;
-} __attribute__((__packed__));
-
-
 extern void kvmclock_init(void);
 
 
@@ -89,7 +71,8 @@ static inline long kvm_hypercall0(unsigned int nr)
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr));
+                     : "a"(nr)
+                     : "memory");
         return ret;
 }
 
@@ -98,7 +81,8 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1));
+                     : "a"(nr), "b"(p1)
+                     : "memory");
         return ret;
 }
 
@@ -108,7 +92,8 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2));
+                     : "a"(nr), "b"(p1), "c"(p2)
+                     : "memory");
         return ret;
 }
 
@@ -118,7 +103,8 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3));
+                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+                     : "memory");
         return ret;
 }
 
@@ -129,7 +115,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
         long ret;
         asm volatile(KVM_HYPERCALL
                      : "=a"(ret)
-                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4));
+                     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
+                     : "memory");
         return ret;
 }
 
diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h
index 56d0e1fa0258..b63c52182006 100644
--- a/include/asm-x86/mach-default/smpboot_hooks.h
+++ b/include/asm-x86/mach-default/smpboot_hooks.h
@@ -41,8 +41,10 @@ static inline void __init smpboot_setup_io_apic(void)
          */
         if (!skip_ioapic_setup && nr_ioapics)
                 setup_IO_APIC();
-        else
+        else {
                 nr_ioapics = 0;
+                localise_nmi_watchdog();
+        }
 }
 
 static inline void smpboot_clear_io_apic(void)
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
new file mode 100644
index 000000000000..95beda07c6fa
--- /dev/null
+++ b/include/asm-x86/mmconfig.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_MMCONFIG_H
+#define _ASM_MMCONFIG_H
+
+#ifdef CONFIG_PCI_MMCONFIG
+extern void __cpuinit fam10h_check_enable_mmcfg(void);
+extern void __init check_enable_amd_mmconf_dmi(void);
+#else
+static inline void fam10h_check_enable_mmcfg(void) { }
+static inline void check_enable_amd_mmconf_dmi(void) { }
+#endif
+
+#endif
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 09413ad39d3c..44bce773012e 100644
--- a/include/asm-x86/msr-index.h
+++ b/include/asm-x86/msr-index.h
@@ -111,7 +111,9 @@
 #define MSR_K8_TOP_MEM2                 0xc001001d
 #define MSR_K8_SYSCFG                   0xc0010010
 #define MSR_K8_HWCR                     0xc0010015
-#define MSR_K8_ENABLE_C1E               0xc0010055
+#define MSR_K8_INT_PENDING_MSG          0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK         0x18000000
 #define MSR_K8_TSEG_ADDR                0xc0010112
 #define K8_MTRRFIXRANGE_DRAM_ENABLE     0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY     0x00080000 /* MtrrFixDramModEn bit */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
index 3707650a169b..2b5f2c91db25 100644
--- a/include/asm-x86/msr.h
+++ b/include/asm-x86/msr.h
@@ -18,7 +18,7 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
         unsigned long low, high;
         asm volatile(".byte 0x0f,0x01,0xf9"
                      : "=a" (low), "=d" (high), "=c" (*aux));
-        return low | ((u64)high >> 32);
+        return low | ((u64)high << 32);
 }
 
 /*
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
index 1e363021e72f..05449ef830a7 100644
--- a/include/asm-x86/nmi.h
+++ b/include/asm-x86/nmi.h
@@ -15,27 +15,6 @@
  */
 int do_nmi_callback(struct pt_regs *regs, int cpu);
 
-#ifdef CONFIG_PM
-
-/** Replace the PM callback routine for NMI. */
-struct pm_dev *set_nmi_pm_callback(pm_callback callback);
-
-/** Unset the PM callback routine back to the default. */
-void unset_nmi_pm_callback(struct pm_dev *dev);
-
-#else
-
-static inline struct pm_dev *set_nmi_pm_callback(pm_callback callback)
-{
-        return 0;
-}
-
-static inline void unset_nmi_pm_callback(struct pm_dev *dev)
-{
-}
-
-#endif /* CONFIG_PM */
-
 #ifdef CONFIG_X86_64
 extern void default_do_nmi(struct pt_regs *);
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
@@ -46,7 +25,6 @@ extern void nmi_watchdog_default(void);
 
 extern int check_nmi_watchdog(void);
 extern int nmi_watchdog_enabled;
-extern int unknown_nmi_panic;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
@@ -78,6 +56,11 @@ extern int unknown_nmi_panic;
 void __trigger_all_cpu_backtrace(void);
 #define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
 
+static inline void localise_nmi_watchdog(void)
+{
+        if (nmi_watchdog == NMI_IO_APIC)
+                nmi_watchdog = NMI_LOCAL_APIC;
+}
 #endif
 
 void lapic_watchdog_stop(void);
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index dc936dddf161..b52ed85f32f5 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -51,8 +51,15 @@
 
 #ifndef __ASSEMBLY__
 
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
+
 extern int page_is_ram(unsigned long pagenr);
 extern int devmem_is_allowed(unsigned long pagenr);
+extern void map_devmem(unsigned long pfn, unsigned long size,
+                       pgprot_t vma_prot);
+extern void unmap_devmem(unsigned long pfn, unsigned long size,
+                         pgprot_t vma_prot);
 
 extern unsigned long max_pfn_mapped;
 
@@ -74,9 +81,6 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
         alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pgprotval_t pgprot; } pgprot_t;
-
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
         return (pgd_t) { val };
@@ -160,6 +164,7 @@ static inline pteval_t native_pte_val(pte_t pte)
 #endif
 
 #define pte_val(x)      native_pte_val(x)
+#define pte_flags(x)    native_pte_val(x)
 #define __pte(x)        native_make_pte(x)
 
 #endif  /* CONFIG_PARAVIRT */
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index 424e82f8ae27..73ed2e4ebf95 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -13,8 +13,17 @@
  */
 #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)
+
+
 #ifdef CONFIG_X86_PAE
-#define __PHYSICAL_MASK_SHIFT   36
+/* 44=32+12, the limit we can fit into an unsigned long pfn */
+#define __PHYSICAL_MASK_SHIFT   44
 #define __VIRTUAL_MASK_SHIFT    32
 #define PAGETABLE_LEVELS        3
 
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 0f13b945e240..e9ada314dfc1 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -238,7 +238,13 @@ struct pv_mmu_ops {
         void (*pte_update_defer)(struct mm_struct *mm,
                                  unsigned long addr, pte_t *ptep);
 
+        pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+                                        pte_t *ptep);
+        void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+                                        pte_t *ptep, pte_t pte);
+
         pteval_t (*pte_val)(pte_t);
+        pteval_t (*pte_flags)(pte_t);
         pte_t (*make_pte)(pteval_t pte);
 
         pgdval_t (*pgd_val)(pgd_t);
@@ -996,6 +1002,20 @@ static inline pteval_t pte_val(pte_t pte)
         return ret;
 }
 
+static inline pteval_t pte_flags(pte_t pte)
+{
+        pteval_t ret;
+
+        if (sizeof(pteval_t) > sizeof(long))
+                ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
+                                 pte.pte, (u64)pte.pte >> 32);
+        else
+                ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
+                                 pte.pte);
+
+        return ret;
+}
+
 static inline pgd_t __pgd(pgdval_t val)
 {
         pgdval_t ret;
@@ -1024,6 +1044,29 @@ static inline pgdval_t pgd_val(pgd_t pgd)
         return ret;
 }
 
+#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+                                           pte_t *ptep)
+{
+        pteval_t ret;
+
+        ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
+                         mm, addr, ptep);
+
+        return (pte_t) { .pte = ret };
+}
+
+static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+                                           pte_t *ptep, pte_t pte)
+{
+        if (sizeof(pteval_t) > sizeof(long))
+                /* 5 arg words */
+                pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+        else
+                PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+                            mm, addr, ptep, pte.pte);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
         if (sizeof(pteval_t) > sizeof(long))
diff --git a/include/asm-x86/pat.h b/include/asm-x86/pat.h
index 88f60cc6a227..7edc47307217 100644
--- a/include/asm-x86/pat.h
+++ b/include/asm-x86/pat.h
@@ -1,14 +1,13 @@
-
 #ifndef _ASM_PAT_H
-#define _ASM_PAT_H 1
+#define _ASM_PAT_H
 
 #include <linux/types.h>
 
 #ifdef CONFIG_X86_PAT
-extern int pat_wc_enabled;
+extern int pat_enabled;
 extern void validate_pat_support(struct cpuinfo_x86 *c);
 #else
-static const int pat_wc_enabled = 0;
+static const int pat_enabled;
 static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
 #endif
 
@@ -21,4 +20,3 @@ extern int free_memtype(u64 start, u64 end);
 extern void pat_disable(char *reason);
 
 #endif
-
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
index 30bbde0cb34b..2db14cf17db8 100644
--- a/include/asm-x86/pci.h
+++ b/include/asm-x86/pci.h
@@ -18,6 +18,8 @@ struct pci_sysdata {
 #endif
 };
 
+extern int pci_routeirq;
+
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
                                             int node);
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
index 8c4c3a0368e2..a50d46851285 100644
--- a/include/asm-x86/pci_32.h
+++ b/include/asm-x86/pci_32.h
@@ -18,12 +18,14 @@ struct pci_dev;
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
 /* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)          (0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)            (0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)   do { } while (0)
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)  sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+        do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)            sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+        do { break; } while (pci_unmap_len(PTR, LEN_NAME))
 
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 97c271b2910b..bcb5446a08d1 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -20,30 +20,25 @@
 #define _PAGE_BIT_PAT_LARGE     12      /* On 2MB or 1GB pages */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
-/*
- * Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
- * sign-extended value on 32-bit with all 1's in the upper word,
- * which preserves the upper pte values on 64-bit ptes:
- */
-#define _PAGE_PRESENT   (_AC(1, L)<<_PAGE_BIT_PRESENT)
-#define _PAGE_RW        (_AC(1, L)<<_PAGE_BIT_RW)
-#define _PAGE_USER      (_AC(1, L)<<_PAGE_BIT_USER)
-#define _PAGE_PWT       (_AC(1, L)<<_PAGE_BIT_PWT)
-#define _PAGE_PCD       (_AC(1, L)<<_PAGE_BIT_PCD)
-#define _PAGE_ACCESSED  (_AC(1, L)<<_PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY     (_AC(1, L)<<_PAGE_BIT_DIRTY)
-#define _PAGE_PSE       (_AC(1, L)<<_PAGE_BIT_PSE)      /* 2MB page */
-#define _PAGE_GLOBAL    (_AC(1, L)<<_PAGE_BIT_GLOBAL)   /* Global TLB entry */
-#define _PAGE_UNUSED1   (_AC(1, L)<<_PAGE_BIT_UNUSED1)
-#define _PAGE_UNUSED2   (_AC(1, L)<<_PAGE_BIT_UNUSED2)
-#define _PAGE_UNUSED3   (_AC(1, L)<<_PAGE_BIT_UNUSED3)
-#define _PAGE_PAT       (_AC(1, L)<<_PAGE_BIT_PAT)
-#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
+#define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
+#define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
+#define _PAGE_PWT       (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
+#define _PAGE_PCD       (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED  (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY     (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE       (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL    (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_UNUSED2   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
+#define _PAGE_UNUSED3   (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
+#define _PAGE_PAT       (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
+#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_NX        (_AC(1, ULL) << _PAGE_BIT_NX)
+#define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else
-#define _PAGE_NX        0
+#define _PAGE_NX        (_AT(pteval_t, 0))
 #endif
 
 /* If _PAGE_PRESENT is clear, we use these: */
@@ -164,37 +159,37 @@ extern struct list_head pgd_list;
  */
 static inline int pte_dirty(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_DIRTY;
+        return pte_flags(pte) & _PAGE_DIRTY;
 }
 
 static inline int pte_young(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_ACCESSED;
+        return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
 static inline int pte_write(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_RW;
+        return pte_flags(pte) & _PAGE_RW;
 }
 
 static inline int pte_file(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_FILE;
+        return pte_flags(pte) & _PAGE_FILE;
 }
 
 static inline int pte_huge(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_PSE;
+        return pte_flags(pte) & _PAGE_PSE;
 }
 
 static inline int pte_global(pte_t pte)
 {
-        return pte_val(pte) & _PAGE_GLOBAL;
+        return pte_flags(pte) & _PAGE_GLOBAL;
 }
 
 static inline int pte_exec(pte_t pte)
 {
-        return !(pte_val(pte) & _PAGE_NX);
+        return !(pte_flags(pte) & _PAGE_NX);
 }
 
 static inline int pte_special(pte_t pte)
@@ -210,22 +205,22 @@ static inline int pmd_large(pmd_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY);
+        return __pte(pte_val(pte) & ~_PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED);
+        return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW);
+        return __pte(pte_val(pte) & ~_PAGE_RW);
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX);
+        return __pte(pte_val(pte) & ~_PAGE_NX);
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -250,7 +245,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 
 static inline pte_t pte_clrhuge(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE);
+        return __pte(pte_val(pte) & ~_PAGE_PSE);
 }
 
 static inline pte_t pte_mkglobal(pte_t pte)
@@ -260,7 +255,7 @@ static inline pte_t pte_mkglobal(pte_t pte)
 
 static inline pte_t pte_clrglobal(pte_t pte)
 {
-        return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
+        return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -305,7 +300,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
         return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK)
+#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_MASK)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
@@ -369,8 +364,15 @@ enum {
         PG_LEVEL_4K,
         PG_LEVEL_2M,
         PG_LEVEL_1G,
+        PG_LEVEL_NUM
 };
 
+#ifdef CONFIG_PROC_FS
+extern void update_page_count(int level, unsigned long pages);
+#else
+static inline void update_page_count(int level, unsigned long pages) { }
+#endif
+
 /*
  * Helper function that returns the kernel pagetable entry controlling
  * the virtual address 'address'. NULL means no pagetable entry present.
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
index 199cab107d85..092b39b3a7e6 100644
--- a/include/asm-x86/processor-flags.h
+++ b/include/asm-x86/processor-flags.h
@@ -88,4 +88,10 @@
 #define CX86_ARR_BASE   0xc4
 #define CX86_RCR_BASE   0xdc
 
+#ifdef CONFIG_VM86
+#define X86_VM_MASK     X86_EFLAGS_VM
+#else
+#define X86_VM_MASK     0 /* No VM86 support */
+#endif
+
 #endif  /* __ASM_I386_PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 559105220a47..4ab2ede6f4b9 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -263,15 +263,11 @@ struct tss_struct {
         struct thread_struct    *io_bitmap_owner;
 
         /*
-         * Pad the TSS to be cacheline-aligned (size is 0x100):
-         */
-        unsigned long           __cacheline_filler[35];
-        /*
          * .. and then another 0x100 bytes for the emergency kernel stack:
          */
         unsigned long           stack[64];
 
-} __attribute__((packed));
+} ____cacheline_aligned;
 
 DECLARE_PER_CPU(struct tss_struct, init_tss);
 
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
index 9f922b0b95d6..8a71db803da6 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -3,7 +3,12 @@
 
 #include <linux/compiler.h>     /* For __user */
 #include <asm/ptrace-abi.h>
+#include <asm/processor-flags.h>
 
+#ifdef __KERNEL__
+#include <asm/ds.h>             /* the DS BTS struct is used for ptrace too */
+#include <asm/segment.h>
+#endif
 
 #ifndef __ASSEMBLY__
 
@@ -55,9 +60,6 @@ struct pt_regs {
         unsigned long ss;
 };
 
-#include <asm/vm86.h>
-#include <asm/segment.h>
-
 #endif /* __KERNEL__ */
 
 #else /* __i386__ */
diff --git a/include/asm-x86/pvclock-abi.h b/include/asm-x86/pvclock-abi.h
new file mode 100644
index 000000000000..6857f840b243
--- /dev/null
+++ b/include/asm-x86/pvclock-abi.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_X86_PVCLOCK_ABI_H_
+#define _ASM_X86_PVCLOCK_ABI_H_
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time.  There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done.  Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+        u32   version;
+        u32   pad0;
+        u64   tsc_timestamp;
+        u64   system_time;
+        u32   tsc_to_system_mul;
+        s8    tsc_shift;
+        u8    pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+        u32   version;
+        u32   sec;
+        u32   nsec;
+} __attribute__((__packed__));
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PVCLOCK_ABI_H_ */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
new file mode 100644
index 000000000000..85b1bba8e0a3
--- /dev/null
+++ b/include/asm-x86/pvclock.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_X86_PVCLOCK_H_
+#define _ASM_X86_PVCLOCK_H_
+
+#include <linux/clocksource.h>
+#include <asm/pvclock-abi.h>
+
+/* some helper functions for xen and kvm pv clock sources */
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
+                            struct pvclock_vcpu_time_info *vcpu,
+                            struct timespec *ts);
+
+#endif /* _ASM_X86_PVCLOCK_H_ */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
index e63741f19392..206f355786dc 100644
--- a/include/asm-x86/reboot.h
+++ b/include/asm-x86/reboot.h
@@ -14,8 +14,8 @@ struct machine_ops {
 
 extern struct machine_ops machine_ops;
 
-void machine_real_restart(unsigned char *code, int length);
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
+void machine_real_restart(const unsigned char *code, int length);
 
 #endif  /* _ASM_REBOOT_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
index 7400d3ad75c6..8c387198ca88 100644
--- a/include/asm-x86/required-features.h
+++ b/include/asm-x86/required-features.h
@@ -19,9 +19,13 @@
 
 #if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
 # define NEED_PAE       (1<<(X86_FEATURE_PAE & 31))
-# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_PAE       0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8       (1<<(X86_FEATURE_CX8 & 31))
+#else
 # define NEED_CX8       0
 #endif
 
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
index 2557514d7ef6..8d9f0b41ee86 100644
--- a/include/asm-x86/resume-trace.h
+++ b/include/asm-x86/resume-trace.h
@@ -6,7 +6,7 @@
 #define TRACE_RESUME(user)                                      \
 do {                                                            \
         if (pm_trace_enabled) {                                 \
-                void *tracedata;                                \
+                const void *tracedata;                          \
                 asm volatile(_ASM_MOV_UL " $1f,%0\n"            \
                              ".section .tracedata,\"a\"\n"      \
                              "1:\t.word %c1\n\t"                \
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
index 18da19e89bff..36e71c5f306f 100644
--- a/include/asm-x86/seccomp_32.h
+++ b/include/asm-x86/seccomp_32.h
@@ -1,4 +1,5 @@
 #ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
 
 #include <linux/thread_info.h>
 
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
index 553af65a2287..76cfe69aa63c 100644
--- a/include/asm-x86/seccomp_64.h
+++ b/include/asm-x86/seccomp_64.h
@@ -1,4 +1,5 @@
 #ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
 
 #include <linux/thread_info.h>
 
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index b49369ad9a61..193578cd1fd9 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -29,81 +29,116 @@ extern char *strchr(const char *s, int c);
 #define __HAVE_ARCH_STRLEN
 extern size_t strlen(const char *s);
 
-static __always_inline void * __memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__memcpy(void *to, const void *from, size_t n)
 {
-int d0, d1, d2;
-__asm__ __volatile__(
-        "rep ; movsl\n\t"
-        "movl %4,%%ecx\n\t"
-        "andl $3,%%ecx\n\t"
-        "jz 1f\n\t"
-        "rep ; movsb\n\t"
-        "1:"
-        : "=&c" (d0), "=&D" (d1), "=&S" (d2)
-        : "0" (n/4), "g" (n), "1" ((long) to), "2" ((long) from)
-        : "memory");
-return (to);
+        int d0, d1, d2;
+        asm volatile("rep ; movsl\n\t"
+                     "movl %4,%%ecx\n\t"
+                     "andl $3,%%ecx\n\t"
+                     "jz 1f\n\t"
+                     "rep ; movsb\n\t"
+                     "1:"
+                     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+                     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
+                     : "memory");
+        return to;
 }
 
 /*
  * This looks ugly, but the compiler can optimize it totally,
  * as the count is constant.
  */
-static __always_inline void * __constant_memcpy(void * to, const void * from, size_t n)
+static __always_inline void *__constant_memcpy(void *to, const void *from,
+                                               size_t n)
 {
         long esi, edi;
-        if (!n) return to;
-#if 1   /* want to do small copies with non-string ops? */
+        if (!n)
+                return to;
+
         switch (n) {
-                case 1: *(char*)to = *(char*)from; return to;
-                case 2: *(short*)to = *(short*)from; return to;
-                case 4: *(int*)to = *(int*)from; return to;
-#if 1   /* including those doable with two moves? */
-                case 3: *(short*)to = *(short*)from;
-                        *((char*)to+2) = *((char*)from+2); return to;
-                case 5: *(int*)to = *(int*)from;
-                        *((char*)to+4) = *((char*)from+4); return to;
-                case 6: *(int*)to = *(int*)from;
-                        *((short*)to+2) = *((short*)from+2); return to;
-                case 8: *(int*)to = *(int*)from;
-                        *((int*)to+1) = *((int*)from+1); return to;
-#endif
+        case 1:
+                *(char *)to = *(char *)from;
+                return to;
+        case 2:
+                *(short *)to = *(short *)from;
+                return to;
+        case 4:
+                *(int *)to = *(int *)from;
+                return to;
+
+        case 3:
+                *(short *)to = *(short *)from;
+                *((char *)to + 2) = *((char *)from + 2);
+                return to;
+        case 5:
+                *(int *)to = *(int *)from;
+                *((char *)to + 4) = *((char *)from + 4);
+                return to;
+        case 6:
+                *(int *)to = *(int *)from;
+                *((short *)to + 2) = *((short *)from + 2);
+                return to;
+        case 8:
+                *(int *)to = *(int *)from;
+                *((int *)to + 1) = *((int *)from + 1);
+                return to;
         }
-#endif
-        esi = (long) from;
-        edi = (long) to;
-        if (n >= 5*4) {
+
+        esi = (long)from;
+        edi = (long)to;
+        if (n >= 5 * 4) {
                 /* large block: use rep prefix */
                 int ecx;
-                __asm__ __volatile__(
-                        "rep ; movsl"
-                        : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
-                        : "0" (n/4), "1" (edi),"2" (esi)
-                        : "memory"
+                asm volatile("rep ; movsl"
+                             : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
+                             : "0" (n / 4), "1" (edi), "2" (esi)
+                             : "memory"
                 );
         } else {
                 /* small block: don't clobber ecx + smaller code */
-                if (n >= 4*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 3*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 2*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                if (n >= 1*4) __asm__ __volatile__("movsl"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
+                if (n >= 4 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 3 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 2 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
+                if (n >= 1 * 4)
+                        asm volatile("movsl"
+                                     : "=&D"(edi), "=&S"(esi)
+                                     : "0"(edi), "1"(esi)
+                                     : "memory");
         }
         switch (n % 4) {
                 /* tail */
-                case 0: return to;
-                case 1: __asm__ __volatile__("movsb"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
-                case 2: __asm__ __volatile__("movsw"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
-                default: __asm__ __volatile__("movsw\n\tmovsb"
-                        :"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
-                        return to;
+        case 0:
+                return to;
+        case 1:
+                asm volatile("movsb"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
+        case 2:
+                asm volatile("movsw"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
+        default:
+                asm volatile("movsw\n\tmovsb"
+                             : "=&D"(edi), "=&S"(esi)
+                             : "0"(edi), "1"(esi)
+                             : "memory");
+                return to;
         }
 }
 
@@ -117,87 +152,86 @@ static __always_inline void * __constant_memcpy(void * to, const void * from, si
  *      This CPU favours 3DNow strongly (eg AMD Athlon)
  */
 
-static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
+static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
 {
         if (len < 512)
                 return __constant_memcpy(to, from, len);
         return _mmx_memcpy(to, from, len);
 }
 
-static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
 {
         if (len < 512)
                 return __memcpy(to, from, len);
         return _mmx_memcpy(to, from, len);
 }
 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy3d((t),(f),(n)) : \
- __memcpy3d((t),(f),(n)))
+#define memcpy(t, f, n)                         \
+        (__builtin_constant_p((n))              \
+         ? __constant_memcpy3d((t), (f), (n))   \
+         : __memcpy3d((t), (f), (n)))
 
 #else
 
 /*
  *      No 3D Now!
  */
- 
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy((t),(f),(n)) : \
- __memcpy((t),(f),(n)))
+
+#define memcpy(t, f, n)                         \
+        (__builtin_constant_p((n))              \
+         ? __constant_memcpy((t), (f), (n))     \
+         : __memcpy((t), (f), (n)))
 
 #endif
 
 #define __HAVE_ARCH_MEMMOVE
-void *memmove(void * dest,const void * src, size_t n);
+void *memmove(void *dest, const void *src, size_t n);
 
 #define memcmp __builtin_memcmp
 
 #define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void * cs,int c,size_t count);
+extern void *memchr(const void *cs, int c, size_t count);
 
-static inline void * __memset_generic(void * s, char c,size_t count)
+static inline void *__memset_generic(void *s, char c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-        "rep\n\t"
-        "stosb"
-        : "=&c" (d0), "=&D" (d1)
-        :"a" (c),"1" (s),"0" (count)
-        :"memory");
-return s;
+        int d0, d1;
+        asm volatile("rep\n\t"
+                     "stosb"
+                     : "=&c" (d0), "=&D" (d1)
+                     : "a" (c), "1" (s), "0" (count)
+                     : "memory");
+        return s;
 }
 
 /* we might want to write optimized versions of these later */
-#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
+#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count))
 
 /*
- * memset(x,0,y) is a reasonably common thing to do, so we want to fill
+ * memset(x, 0, y) is a reasonably common thing to do, so we want to fill
  * things 32 bits at a time even when we don't know the size of the
  * area at compile-time..
  */
-static __always_inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
+static __always_inline
+void *__constant_c_memset(void *s, unsigned long c, size_t count)
 {
-int d0, d1;
-__asm__ __volatile__(
-        "rep ; stosl\n\t"
-        "testb $2,%b3\n\t"
-        "je 1f\n\t"
-        "stosw\n"
-        "1:\ttestb $1,%b3\n\t"
-        "je 2f\n\t"
-        "stosb\n"
-        "2:"
-        :"=&c" (d0), "=&D" (d1)
-        :"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
-        :"memory");
-return (s);     
+        int d0, d1;
+        asm volatile("rep ; stosl\n\t"
+                     "testb $2,%b3\n\t"
+                     "je 1f\n\t"
+                     "stosw\n"
+                     "1:\ttestb $1,%b3\n\t"
+                     "je 2f\n\t"
+                     "stosb\n"
+                     "2:"
+                     : "=&c" (d0), "=&D" (d1)
+                     : "a" (c), "q" (count), "0" (count/4), "1" ((long)s)
+                     : "memory");
+        return s;
 }
 
 /* Added by Gertjan van Wingerde to make minix and sysv module work */
 #define __HAVE_ARCH_STRNLEN
-extern size_t strnlen(const char * s, size_t count);
+extern size_t strnlen(const char *s, size_t count);
 /* end of additional stuff */
 
 #define __HAVE_ARCH_STRSTR
@@ -207,66 +241,85 @@ extern char *strstr(const char *cs, const char *ct);
  * This looks horribly ugly, but the compiler can optimize it totally,
  * as we by now know that both pattern and count is constant..
  */
-static __always_inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
+static __always_inline
+void *__constant_c_and_count_memset(void *s, unsigned long pattern,
+                                    size_t count)
 {
         switch (count) {
+        case 0:
+                return s;
+        case 1:
+                *(unsigned char *)s = pattern & 0xff;
+                return s;
+        case 2:
+                *(unsigned short *)s = pattern & 0xffff;
+                return s;
+        case 3:
+                *(unsigned short *)s = pattern & 0xffff;
+                *((unsigned char *)s + 2) = pattern & 0xff;
+                return s;
+        case 4:
+                *(unsigned long *)s = pattern;
+                return s;
+        }
+
+#define COMMON(x)                                                       \
+        asm volatile("rep ; stosl"                                      \
+                     x                                                  \
+                     : "=&c" (d0), "=&D" (d1)                           \
+                     : "a" (eax), "0" (count/4), "1" ((long)s)  \
+                     : "memory")
+
+        {
+                int d0, d1;
+#if __GNUC__ == 4 && __GNUC_MINOR__ == 0
+                /* Workaround for broken gcc 4.0 */
+                register unsigned long eax asm("%eax") = pattern;
+#else
+                unsigned long eax = pattern;
+#endif
+
+                switch (count % 4) {
                 case 0:
+                        COMMON("");
                         return s;
                 case 1:
-                        *(unsigned char *)s = pattern & 0xff;
+                        COMMON("\n\tstosb");
                         return s;
                 case 2:
-                        *(unsigned short *)s = pattern & 0xffff;
+                        COMMON("\n\tstosw");
                         return s;
-                case 3:
-                        *(unsigned short *)s = pattern & 0xffff;
-                        *(2+(unsigned char *)s) = pattern & 0xff;
-                        return s;
-                case 4:
-                        *(unsigned long *)s = pattern;
+                default:
+                        COMMON("\n\tstosw\n\tstosb");
                         return s;
+                }
         }
-#define COMMON(x) \
-__asm__  __volatile__( \
-        "rep ; stosl" \
-        x \
-        : "=&c" (d0), "=&D" (d1) \
-        : "a" (pattern),"0" (count/4),"1" ((long) s) \
-        : "memory")
-{
-        int d0, d1;
-        switch (count % 4) {
-                case 0: COMMON(""); return s;
-                case 1: COMMON("\n\tstosb"); return s;
-                case 2: COMMON("\n\tstosw"); return s;
-                default: COMMON("\n\tstosw\n\tstosb"); return s;
-        }
-}
-  
+
 #undef COMMON
 }
 
-#define __constant_c_x_memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_c_and_count_memset((s),(c),(count)) : \
- __constant_c_memset((s),(c),(count)))
+#define __constant_c_x_memset(s, c, count)                      \
+        (__builtin_constant_p(count)                            \
+         ? __constant_c_and_count_memset((s), (c), (count))     \
+         : __constant_c_memset((s), (c), (count)))
 
-#define __memset(s, c, count) \
-(__builtin_constant_p(count) ? \
- __constant_count_memset((s),(c),(count)) : \
- __memset_generic((s),(c),(count)))
+#define __memset(s, c, count)                           \
+        (__builtin_constant_p(count)                    \
+         ? __constant_count_memset((s), (c), (count))   \
+         : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) \
-(__builtin_constant_p(c) ? \
- __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
- __memset((s),(c),(count)))
+#define memset(s, c, count)                                             \
+        (__builtin_constant_p(c)                                        \
+         ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
+                                 (count))                               \
+         : __memset((s), (c), (count)))
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
  */
 #define __HAVE_ARCH_MEMSCAN
-extern void *memscan(void * addr, int c, size_t size);
+extern void *memscan(void *addr, int c, size_t size);
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
index 24e1c080aa8a..8675c6782a7d 100644
--- a/include/asm-x86/suspend_32.h
+++ b/include/asm-x86/suspend_32.h
@@ -3,6 +3,9 @@
  * Based on code
  * Copyright 2001 Patrick Mochel <mochel@osdl.org>
  */
+#ifndef __ASM_X86_32_SUSPEND_H
+#define __ASM_X86_32_SUSPEND_H
+
 #include <asm/desc.h>
 #include <asm/i387.h>
 
@@ -44,3 +47,5 @@ static inline void acpi_save_register_state(unsigned long return_point)
 /* routines for saving/restoring kernel state */
 extern int acpi_save_state_mem(void);
 #endif
+
+#endif /* __ASM_X86_32_SUSPEND_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index a2f04cd79b29..7e4c133795a1 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -289,7 +289,7 @@ static inline void native_wbinvd(void)
 
 #endif/* CONFIG_PARAVIRT */
 
-#define stts() write_cr0(8 | read_cr0())
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index 77244f17993f..895339d2bc0b 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -1,9 +1,253 @@
+/* thread_info.h: low-level thread information
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+
 #ifndef _ASM_X86_THREAD_INFO_H
+#define _ASM_X86_THREAD_INFO_H
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/types.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ */
+#ifndef __ASSEMBLY__
+struct task_struct;
+struct exec_domain;
+#include <asm/processor.h>
+
+struct thread_info {
+        struct task_struct      *task;          /* main task structure */
+        struct exec_domain      *exec_domain;   /* execution domain */
+        unsigned long           flags;          /* low level flags */
+        __u32                   status;         /* thread synchronous flags */
+        __u32                   cpu;            /* current CPU */
+        int                     preempt_count;  /* 0 => preemptable,
+                                                   <0 => BUG */
+        mm_segment_t            addr_limit;
+        struct restart_block    restart_block;
+        void __user             *sysenter_return;
+#ifdef CONFIG_X86_32
+        unsigned long           previous_esp;   /* ESP of the previous stack in
+                                                   case of nested (IRQ) stacks
+                                                */
+        __u8                    supervisor_stack[0];
+#endif
+};
+
+#define INIT_THREAD_INFO(tsk)                   \
+{                                               \
+        .task           = &tsk,                 \
+        .exec_domain    = &default_exec_domain, \
+        .flags          = 0,                    \
+        .cpu            = 0,                    \
+        .preempt_count  = 1,                    \
+        .addr_limit     = KERNEL_DS,            \
+        .restart_block = {                      \
+                .fn = do_no_restart_syscall,    \
+        },                                      \
+}
+
+#define init_thread_info        (init_thread_union.thread_info)
+#define init_stack              (init_thread_union.stack)
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+
+#endif
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files
+ *   may need to access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ * Warning: layout of LSW is hardcoded in entry.S
+ */
+#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
+#define TIF_SIGPENDING          2       /* signal pending */
+#define TIF_NEED_RESCHED        3       /* rescheduling necessary */
+#define TIF_SINGLESTEP          4       /* reenable singlestep on user return*/
+#define TIF_IRET                5       /* force IRET */
 #ifdef CONFIG_X86_32
-# include "thread_info_32.h"
+#define TIF_SYSCALL_EMU         6       /* syscall emulation active */
+#endif
+#define TIF_SYSCALL_AUDIT       7       /* syscall auditing active */
+#define TIF_SECCOMP             8       /* secure computing */
+#define TIF_MCE_NOTIFY          10      /* notify userspace of an MCE */
+#define TIF_HRTICK_RESCHED      11      /* reprogram hrtick timer */
+#define TIF_NOTSC               16      /* TSC is not accessible in userland */
+#define TIF_IA32                17      /* 32bit process */
+#define TIF_FORK                18      /* ret_from_fork */
+#define TIF_ABI_PENDING         19
+#define TIF_MEMDIE              20
+#define TIF_DEBUG               21      /* uses debug registers */
+#define TIF_IO_BITMAP           22      /* uses I/O bitmap */
+#define TIF_FREEZE              23      /* is freezing for suspend */
+#define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
+#define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
+#define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
+#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
+
+#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
+#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
+#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
+#define _TIF_IRET               (1 << TIF_IRET)
+#ifdef CONFIG_X86_32
+#define _TIF_SYSCALL_EMU        (1 << TIF_SYSCALL_EMU)
 #else
-# include "thread_info_64.h"
+#define _TIF_SYSCALL_EMU        0
 #endif
+#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
+#define _TIF_MCE_NOTIFY         (1 << TIF_MCE_NOTIFY)
+#define _TIF_HRTICK_RESCHED     (1 << TIF_HRTICK_RESCHED)
+#define _TIF_NOTSC              (1 << TIF_NOTSC)
+#define _TIF_IA32               (1 << TIF_IA32)
+#define _TIF_FORK               (1 << TIF_FORK)
+#define _TIF_ABI_PENDING        (1 << TIF_ABI_PENDING)
+#define _TIF_DEBUG              (1 << TIF_DEBUG)
+#define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
+#define _TIF_FREEZE             (1 << TIF_FREEZE)
+#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
+#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
+#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
+#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK                                                  \
+        (0x0000FFFF &                                                   \
+         ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|       \
+         _TIF_SECCOMP|_TIF_SYSCALL_EMU))
+
+/* work to do on any return to user space */
+#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+
+/* Only used for 64 bit */
+#define _TIF_DO_NOTIFY_MASK                                             \
+        (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
+
+/* flags to check in __switch_to() */
+#define _TIF_WORK_CTXSW                                                 \
+        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
+                                                                _TIF_NOTSC)
+
+#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
+
+#define PREEMPT_ACTIVE          0x10000000
+
+/* thread information allocation */
+#ifdef CONFIG_DEBUG_STACK_USAGE
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
+#else
+#define THREAD_FLAGS GFP_KERNEL
+#endif
+
+#define alloc_thread_info(tsk)                                          \
+        ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+
+#ifdef CONFIG_X86_32
+
+#define STACK_WARN      (THREAD_SIZE/8)
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("esp") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+        return (struct thread_info *)
+                (current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg)     \
+        movl $-THREAD_SIZE, reg; \
+        andl %esp, reg
+
+/* use this one if reg already contains %esp */
+#define GET_THREAD_INFO_WITH_ESP(reg) \
+        andl $-THREAD_SIZE, reg
+
+#endif
+
+#else /* X86_32 */
+
+#include <asm/pda.h>
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+static inline struct thread_info *current_thread_info(void)
+{
+        struct thread_info *ti;
+        ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
+        return ti;
+}
+
+/* do not use in interrupt context */
+static inline struct thread_info *stack_thread_info(void)
+{
+        struct thread_info *ti;
+        asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+        return ti;
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg) \
+        movq %gs:pda_kernelstack,reg ; \
+        subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+
+#endif
+
+#endif /* !X86_32 */
+
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_USEDFPU              0x0001  /* FPU was used by this task
+                                           this quantum (SMP) */
+#define TS_COMPAT               0x0002  /* 32bit syscall active (64BIT)*/
+#define TS_POLLING              0x0004  /* true if in idle loop
+                                           and not sleeping */
+#define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
+
+#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#ifndef __ASSEMBLY__
+#define HAVE_SET_RESTORE_SIGMASK        1
+static inline void set_restore_sigmask(void)
+{
+        struct thread_info *ti = current_thread_info();
+        ti->status |= TS_RESTORE_SIGMASK;
+        set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
+}
+#endif  /* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
 extern void arch_task_cache_init(void);
diff --git a/include/asm-x86/thread_info_32.h b/include/asm-x86/thread_info_32.h
deleted file mode 100644
index b6338829d1a8..000000000000
--- a/include/asm-x86/thread_info_32.h
+++ /dev/null
@@ -1,205 +0,0 @@
-/* thread_info.h: i386 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-#include <asm/page.h>
-
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-#endif
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- * - if the contents of this structure are changed,
- *   the assembly constants must also be changed
- */
-#ifndef __ASSEMBLY__
-
-struct thread_info {
-        struct task_struct      *task;          /* main task structure */
-        struct exec_domain      *exec_domain;   /* execution domain */
-        unsigned long           flags;          /* low level flags */
-        unsigned long           status;         /* thread-synchronous flags */
-        __u32                   cpu;            /* current CPU */
-        int                     preempt_count;  /* 0 => preemptable,
-                                                   <0 => BUG */
-        mm_segment_t            addr_limit;     /* thread address space:
-                                                   0-0xBFFFFFFF user-thread
-                                                   0-0xFFFFFFFF kernel-thread
-                                                */
-        void                    *sysenter_return;
-        struct restart_block    restart_block;
-        unsigned long           previous_esp;   /* ESP of the previous stack in
-                                                   case of nested (IRQ) stacks
-                                                */
-        __u8                    supervisor_stack[0];
-};
-
-#else /* !__ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-
-#endif
-
-#define PREEMPT_ACTIVE          0x10000000
-#ifdef CONFIG_4KSTACKS
-#define THREAD_SIZE            (4096)
-#else
-#define THREAD_SIZE             (8192)
-#endif
-
-#define STACK_WARN             (THREAD_SIZE/8)
-/*
- * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-
-#define INIT_THREAD_INFO(tsk)                   \
-{                                               \
-        .task           = &tsk,                 \
-        .exec_domain    = &default_exec_domain, \
-        .flags          = 0,                    \
-        .cpu            = 0,                    \
-        .preempt_count  = 1,                    \
-        .addr_limit     = KERNEL_DS,            \
-        .restart_block = {                      \
-                .fn = do_no_restart_syscall,    \
-        },                                      \
-}
-
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
-
-/* how to get the current stack pointer from C */
-register unsigned long current_stack_pointer asm("esp") __used;
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-        return (struct thread_info *)
-                (current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define alloc_thread_info(tsk) ((struct thread_info *)                  \
-        __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(THREAD_SIZE)))
-#else
-#define alloc_thread_info(tsk) ((struct thread_info *)                  \
-        __get_free_pages(GFP_KERNEL, get_order(THREAD_SIZE)))
-#endif
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)     \
-        movl $-THREAD_SIZE, reg; \
-        andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-        andl $-THREAD_SIZE, reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various
- *   assembly files may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- */
-#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
-#define TIF_SIGPENDING          1       /* signal pending */
-#define TIF_NEED_RESCHED        2       /* rescheduling necessary */
-#define TIF_SINGLESTEP          3       /* restore singlestep on return to
-                                           user mode */
-#define TIF_IRET                4       /* return with iret */
-#define TIF_SYSCALL_EMU         5       /* syscall emulation active */
-#define TIF_SYSCALL_AUDIT       6       /* syscall auditing active */
-#define TIF_SECCOMP             7       /* secure computing */
-#define TIF_HRTICK_RESCHED      9       /* reprogram hrtick timer */
-#define TIF_MEMDIE              16
-#define TIF_DEBUG               17      /* uses debug registers */
-#define TIF_IO_BITMAP           18      /* uses I/O bitmap */
-#define TIF_FREEZE              19      /* is freezing for suspend */
-#define TIF_NOTSC               20      /* TSC is not accessible in userland */
-#define TIF_FORCED_TF           21      /* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR         22      /* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR         23      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        24      /* record scheduling event timestamps */
-
-#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
-#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
-#define _TIF_IRET               (1 << TIF_IRET)
-#define _TIF_SYSCALL_EMU        (1 << TIF_SYSCALL_EMU)
-#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
-#define _TIF_HRTICK_RESCHED     (1 << TIF_HRTICK_RESCHED)
-#define _TIF_DEBUG              (1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE             (1 << TIF_FREEZE)
-#define _TIF_NOTSC              (1 << TIF_NOTSC)
-#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK                                                  \
-        (0x0000FFFF & ~(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |       \
-                        _TIF_SECCOMP | _TIF_SYSCALL_EMU))
-/* work to do on any return to u-space */
-#define _TIF_ALLWORK_MASK       (0x0000FFFF & ~_TIF_SECCOMP)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW                                         \
-        (_TIF_IO_BITMAP | _TIF_NOTSC | _TIF_DEBUGCTLMSR |       \
-         _TIF_DS_AREA_MSR | _TIF_BTS_TRACE_TS)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW | _TIF_DEBUG)
-
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU              0x0001  /* FPU was used by this task
-                                           this quantum (SMP) */
-#define TS_POLLING              0x0002  /* True if in idle loop
-                                           and not sleeping */
-#define TS_RESTORE_SIGMASK      0x0004  /* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK        1
-static inline void set_restore_sigmask(void)
-{
-        struct thread_info *ti = current_thread_info();
-        ti->status |= TS_RESTORE_SIGMASK;
-        set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif  /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
deleted file mode 100644
index cb69f70abba1..000000000000
--- a/include/asm-x86/thread_info_64.h
+++ /dev/null
@@ -1,195 +0,0 @@
-/* thread_info.h: x86_64 low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#include <asm/page.h>
-#include <asm/types.h>
-#include <asm/pda.h>
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- */
-#ifndef __ASSEMBLY__
-struct task_struct;
-struct exec_domain;
-#include <asm/processor.h>
-
-struct thread_info {
-        struct task_struct      *task;          /* main task structure */
-        struct exec_domain      *exec_domain;   /* execution domain */
-        __u32                   flags;          /* low level flags */
-        __u32                   status;         /* thread synchronous flags */
-        __u32                   cpu;            /* current CPU */
-        int                     preempt_count;  /* 0 => preemptable,
-                                                   <0 => BUG */
-        mm_segment_t            addr_limit;
-        struct restart_block    restart_block;
-#ifdef CONFIG_IA32_EMULATION
-        void __user             *sysenter_return;
-#endif
-};
-#endif
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-#define INIT_THREAD_INFO(tsk)                   \
-{                                               \
-        .task          = &tsk,                  \
-        .exec_domain   = &default_exec_domain,  \
-        .flags         = 0,                     \
-        .cpu           = 0,                     \
-        .preempt_count = 1,                     \
-        .addr_limit     = KERNEL_DS,            \
-        .restart_block = {                      \
-                .fn = do_no_restart_syscall,    \
-        },                                      \
-}
-
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
-static inline struct thread_info *current_thread_info(void)
-{
-        struct thread_info *ti;
-        ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-        return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
-        struct thread_info *ti;
-        asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
-        return ti;
-}
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
-#else
-#define THREAD_FLAGS GFP_KERNEL
-#endif
-
-#define alloc_thread_info(tsk)                                          \
-        ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg) \
-        movq %gs:pda_kernelstack,reg ; \
-        subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various assembly files
- *   may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- * Warning: layout of LSW is hardcoded in entry.S
- */
-#define TIF_SYSCALL_TRACE       0       /* syscall trace active */
-#define TIF_SIGPENDING          2       /* signal pending */
-#define TIF_NEED_RESCHED        3       /* rescheduling necessary */
-#define TIF_SINGLESTEP          4       /* reenable singlestep on user return*/
-#define TIF_IRET                5       /* force IRET */
-#define TIF_SYSCALL_AUDIT       7       /* syscall auditing active */
-#define TIF_SECCOMP             8       /* secure computing */
-#define TIF_MCE_NOTIFY          10      /* notify userspace of an MCE */
-#define TIF_HRTICK_RESCHED      11      /* reprogram hrtick timer */
-/* 16 free */
-#define TIF_IA32                17      /* 32bit process */
-#define TIF_FORK                18      /* ret_from_fork */
-#define TIF_ABI_PENDING         19
-#define TIF_MEMDIE              20
-#define TIF_DEBUG               21      /* uses debug registers */
-#define TIF_IO_BITMAP           22      /* uses I/O bitmap */
-#define TIF_FREEZE              23      /* is freezing for suspend */
-#define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
-#define TIF_NOTSC               28      /* TSC is not accessible in userland */
-
-#define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING         (1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP         (1 << TIF_SINGLESTEP)
-#define _TIF_NEED_RESCHED       (1 << TIF_NEED_RESCHED)
-#define _TIF_IRET               (1 << TIF_IRET)
-#define _TIF_SYSCALL_AUDIT      (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP            (1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY         (1 << TIF_MCE_NOTIFY)
-#define _TIF_HRTICK_RESCHED     (1 << TIF_HRTICK_RESCHED)
-#define _TIF_IA32               (1 << TIF_IA32)
-#define _TIF_FORK               (1 << TIF_FORK)
-#define _TIF_ABI_PENDING        (1 << TIF_ABI_PENDING)
-#define _TIF_DEBUG              (1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP          (1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE             (1 << TIF_FREEZE)
-#define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
-#define _TIF_NOTSC              (1 << TIF_NOTSC)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK                                                  \
-        (0x0000FFFF &                                                   \
-         ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|_TIF_SECCOMP))
-/* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
-
-#define _TIF_DO_NOTIFY_MASK                                             \
-        (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW                                                 \
-        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS|_TIF_NOTSC)
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
-
-#define PREEMPT_ACTIVE     0x10000000
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU              0x0001  /* FPU was used by this task
-                                           this quantum (SMP) */
-#define TS_COMPAT               0x0002  /* 32bit syscall active */
-#define TS_POLLING              0x0004  /* true if in idle loop
-                                           and not sleeping */
-#define TS_RESTORE_SIGMASK      0x0008  /* restore signal mask in do_signal() */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK        1
-static inline void set_restore_sigmask(void)
-{
-        struct thread_info *ti = current_thread_info();
-        ti->status |= TS_RESTORE_SIGMASK;
-        set_bit(TIF_SIGPENDING, &ti->flags);
-}
-#endif  /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index fe26e36d0f51..9c1a4a3470d9 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -290,7 +290,7 @@ __SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
 #define __NR_rt_sigqueueinfo                    129
 __SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
 #define __NR_rt_sigsuspend                      130
-__SYSCALL(__NR_rt_sigsuspend, stub_rt_sigsuspend)
+__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
 #define __NR_sigaltstack                        131
 __SYSCALL(__NR_sigaltstack, stub_sigaltstack)
 #define __NR_utime                              132
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
index 074b357146df..5ce351325e01 100644
--- a/include/asm-x86/vm86.h
+++ b/include/asm-x86/vm86.h
@@ -14,12 +14,6 @@
 
 #include <asm/processor-flags.h>
 
-#ifdef CONFIG_VM86
-#define X86_VM_MASK     X86_EFLAGS_VM
-#else
-#define X86_VM_MASK     0 /* No VM86 support */
-#endif
-
 #define BIOSSEG         0x0f000
 
 #define CPU_086         0
@@ -121,7 +115,6 @@ struct vm86plus_info_struct {
         unsigned long is_vm86pus:1;           /* for vm86 internal use */
         unsigned char vm86dbg_intxxtab[32];   /* for debugger */
 };
-
 struct vm86plus_struct {
         struct vm86_regs regs;
         unsigned long flags;
@@ -133,6 +126,9 @@ struct vm86plus_struct {
 };
 
 #ifdef __KERNEL__
+
+#include <asm/ptrace.h>
+
 /*
  * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86
  * mode - the main change is that the old segment descriptors aren't
@@ -141,7 +137,6 @@ struct vm86plus_struct {
  * at the end of the structure. Look at ptrace.h to see the "normal"
  * setup. For user space layout see 'struct vm86_regs' above.
  */
-#include <asm/ptrace.h>
 
 struct kernel_vm86_regs {
 /*
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index c2ccd997ed35..2a4f9b41d684 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -176,9 +176,9 @@ HYPERVISOR_fpu_taskswitch(int set)
 }
 
 static inline int
-HYPERVISOR_sched_op(int cmd, unsigned long arg)
+HYPERVISOR_sched_op(int cmd, void *arg)
 {
-        return _hypercall2(int, sched_op, cmd, arg);
+        return _hypercall2(int, sched_op_new, cmd, arg);
 }
 
 static inline long
@@ -315,6 +315,13 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
 }
 
 static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+        mcl->op = __HYPERVISOR_fpu_taskswitch;
+        mcl->args[0] = set;
+}
+
+static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
                         pte_t new_val, unsigned long flags)
 {
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index baf3a4dce28c..377c04591c15 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -26,15 +26,20 @@ typedef struct xpaddr {
 #define FOREIGN_FRAME_BIT       (1UL<<31)
 #define FOREIGN_FRAME(m)        ((m) | FOREIGN_FRAME_BIT)
 
-extern unsigned long *phys_to_machine_mapping;
+/* 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 get_phys_to_machine(unsigned long pfn);
+extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return pfn;
 
-        return phys_to_machine_mapping[(unsigned int)(pfn)] &
-                ~FOREIGN_FRAME_BIT;
+        return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -42,7 +47,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return 1;
 
-        return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY);
+        return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
@@ -106,20 +111,12 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
         unsigned long pfn = mfn_to_pfn(mfn);
         if ((pfn < max_mapnr)
             && !xen_feature(XENFEAT_auto_translated_physmap)
-            && (phys_to_machine_mapping[pfn] != mfn))
+            && (get_phys_to_machine(pfn) != mfn))
                 return max_mapnr; /* force !pfn_valid() */
+        /* XXX fixme; not true with sparsemem */
         return pfn;
 }
 
-static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-        if (xen_feature(XENFEAT_auto_translated_physmap)) {
-                BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-                return;
-        }
-        phys_to_machine_mapping[pfn] = mfn;
-}
-
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)      (phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)          (pfn_to_mfn(PFN_DOWN(__pa(v))))
@@ -150,13 +147,9 @@ static inline pte_t __pte_ma(pteval_t x)
         return (pte_t) { .pte = x };
 }
 
-#ifdef CONFIG_X86_PAE
 #define pmd_val_ma(v) ((v).pmd)
 #define pud_val_ma(v) ((v).pgd.pgd)
 #define __pmd_ma(x)     ((pmd_t) { (x) } )
-#else  /* !X86_PAE */
-#define pmd_val_ma(v)   ((v).pud.pgd.pgd)
-#endif  /* CONFIG_X86_PAE */
 
 #define pgd_val_ma(x)   ((x).pgd)
 
diff --git a/include/asm-x86/xor_32.h b/include/asm-x86/xor_32.h
index 067b5c1835a3..921b45840449 100644
--- a/include/asm-x86/xor_32.h
+++ b/include/asm-x86/xor_32.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_32_H
+#define ASM_X86__XOR_32_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -881,3 +884,5 @@ do {							\
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST)                    \
         (cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
+
+#endif /* ASM_X86__XOR_32_H */
diff --git a/include/asm-x86/xor_64.h b/include/asm-x86/xor_64.h
index 24957e39ac8a..2d3a18de295b 100644
--- a/include/asm-x86/xor_64.h
+++ b/include/asm-x86/xor_64.h
@@ -1,3 +1,6 @@
+#ifndef ASM_X86__XOR_64_H
+#define ASM_X86__XOR_64_H
+
 /*
  * Optimized RAID-5 checksumming functions for MMX and SSE.
  *
@@ -354,3 +357,5 @@ do {						\
    We may also be able to load into the L1 only depending on how the cpu
    deals with a load to a line that is being prefetched.  */
 #define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
+
+#endif /* ASM_X86__XOR_64_H */
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 93b98856007a..71d70d1fbce2 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -166,6 +166,9 @@ unifdef-y += acct.h
 unifdef-y += adb.h
 unifdef-y += adfs_fs.h
 unifdef-y += agpgart.h
+ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/a.out.h),)
+unifdef-y += a.out.h
+endif
 unifdef-y += apm_bios.h
 unifdef-y += atalk.h
 unifdef-y += atmdev.h
diff --git a/include/linux/a.out.h b/include/linux/a.out.h
index 208f4e8ed304..e86dfca44589 100644
--- a/include/linux/a.out.h
+++ b/include/linux/a.out.h
@@ -1,8 +1,6 @@
 #ifndef __A_OUT_GNU_H__
 #define __A_OUT_GNU_H__
 
-#ifdef CONFIG_ARCH_SUPPORTS_AOUT
-
 #define __GNU_EXEC_MACROS__
 
 #ifndef __STRUCT_EXEC_OVERRIDE__
@@ -277,10 +275,4 @@ struct relocation_info
 #endif /* no N_RELOCATION_INFO_DECLARED.  */
 
 #endif /*__ASSEMBLY__ */
-#else /* CONFIG_ARCH_SUPPORTS_AOUT */
-#ifndef __ASSEMBLY__
-struct exec {
-};
-#endif
-#endif /* CONFIG_ARCH_SUPPORTS_AOUT */
 #endif /* __A_OUT_GNU_H__ */
diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h
index 661d90d6cf7c..972b12bcfb36 100644
--- a/include/linux/agp_backend.h
+++ b/include/linux/agp_backend.h
@@ -30,14 +30,6 @@
 #ifndef _AGP_BACKEND_H
 #define _AGP_BACKEND_H 1
 
-#ifndef TRUE
-#define TRUE 1
-#endif
-
-#ifndef FALSE
-#define FALSE 0
-#endif
-
 enum chipset_type {
         NOT_SUPPORTED,
         SUPPORTED,
@@ -57,7 +49,7 @@ struct agp_kern_info {
         size_t aper_size;
         int max_memory;         /* In pages */
         int current_memory;
-        int cant_use_aperture;
+        bool cant_use_aperture;
         unsigned long page_mask;
         struct vm_operations_struct *vm_ops;
 };
@@ -83,9 +75,9 @@ struct agp_memory {
         off_t pg_start;
         u32 type;
         u32 physical;
-        u8 is_bound;
-        u8 is_flushed;
-        u8 vmalloc_flag;
+        bool is_bound;
+        bool is_flushed;
+        bool vmalloc_flag;
 };
 
 #define AGP_NORMAL_MEMORY 0
diff --git a/include/linux/agpgart.h b/include/linux/agpgart.h
index 62aef589eb94..c8fdb6e658e1 100644
--- a/include/linux/agpgart.h
+++ b/include/linux/agpgart.h
@@ -206,8 +206,8 @@ struct agp_front_data {
         struct agp_controller *current_controller;
         struct agp_controller *controllers;
         struct agp_file_private *file_priv_list;
-        u8 used_by_controller;
-        u8 backend_acquired;
+        bool used_by_controller;
+        bool backend_acquired;
 };
 
 #endif                          /* __KERNEL__ */
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 63c3bb98558f..8b82974bdc12 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -571,7 +571,7 @@ extern void		    audit_log_lost(const char *message);
 extern int                  audit_update_lsm_rules(void);
 
                                 /* Private API (for audit.c only) */
-extern int audit_filter_user(struct netlink_skb_parms *cb, int type);
+extern int audit_filter_user(struct netlink_skb_parms *cb);
 extern int audit_filter_type(int type);
 extern int  audit_receive_filter(int type, int pid, int uid, int seq,
                                 void *data, size_t datasz, uid_t loginuid,
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 6a5dbdc8a7dc..686895bacd9d 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -94,7 +94,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
                                        unsigned long freepfn,
                                        unsigned long startpfn,
                                        unsigned long endpfn);
-extern void reserve_bootmem_node(pg_data_t *pgdat,
+extern int reserve_bootmem_node(pg_data_t *pgdat,
                                  unsigned long physaddr,
                                  unsigned long size,
                                  int flags);
diff --git a/include/linux/capability.h b/include/linux/capability.h
index fa830f8de032..02673846d205 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -501,6 +501,8 @@ extern const kernel_cap_t __cap_empty_set;
 extern const kernel_cap_t __cap_full_set;
 extern const kernel_cap_t __cap_init_eff_set;
 
+kernel_cap_t cap_set_effective(const kernel_cap_t pE_new);
+
 int capable(int cap);
 int __capable(struct task_struct *t, int cap);
 
diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h
index 1605dd8aa646..6f9f19d66591 100644
--- a/include/linux/cfag12864b.h
+++ b/include/linux/cfag12864b.h
@@ -4,7 +4,7 @@
  * Description: cfag12864b LCD driver header
  *     License: GPLv2
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-12
  *
  *  This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/console.h b/include/linux/console.h
index a4f27fbdf549..248e6e3b9b73 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -108,6 +108,8 @@ struct console {
         struct   console *next;
 };
 
+extern int console_set_on_cmdline;
+
 extern int add_preferred_console(char *name, int idx, char *options);
 extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options);
 extern void register_console(struct console *);
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 5df3db58fcc6..c24875bd9c5b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -353,6 +353,10 @@ static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp,
         for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #endif /* NR_CPUS */
 
+#define next_cpu_nr(n, src)             next_cpu(n, src)
+#define cpus_weight_nr(cpumask)         cpus_weight(cpumask)
+#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask)
+
 /*
  * The following particular system cpumasks and operations manage
  * possible, present and online cpus.  Each of them is a fixed size
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 2a6639407c80..d982eb89c77d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -300,7 +300,7 @@ extern int d_validate(struct dentry *, struct dentry *);
 extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
 
 extern char *__d_path(const struct path *path, struct path *root, char *, int);
-extern char *d_path(struct path *, char *, int);
+extern char *d_path(const struct path *, char *, int);
 extern char *dentry_path(struct dentry *, char *, int);
 
 /* Allocation counts.. */
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index f4a5871767f5..4aaa4afb1cb9 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_DEBUG_LOCKING_H
 #define __LINUX_DEBUG_LOCKING_H
 
+#include <linux/kernel.h>
+
 struct task_struct;
 
 extern int debug_locks;
@@ -11,14 +13,6 @@ extern int debug_locks_silent;
  */
 extern int debug_locks_off(void);
 
-/*
- * In the debug case we carry the caller's instruction pointer into
- * other functions, but we dont want the function argument overhead
- * in the nondebug case - hence these macros:
- */
-#define _RET_IP_                (unsigned long)__builtin_return_address(0)
-#define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
-
 #define DEBUG_LOCKS_WARN_ON(c)                                          \
 ({                                                                      \
         int __ret = 0;                                                  \
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index 4d10c7328d2d..6c7eff2ebada 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -13,7 +13,7 @@ struct firmware {
 
 struct device;
 
-#if defined(CONFIG_FW_LOADER) || defined(CONFIG_FW_LOADER_MODULE)
+#if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE))
 int request_firmware(const struct firmware **fw, const char *name,
                      struct device *device);
 int request_firmware_nowait(
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d490779f18d9..d8e2762ed14d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -83,6 +83,7 @@ extern int dir_notify_enable;
 #define READ_SYNC       (READ | (1 << BIO_RW_SYNC))
 #define READ_META       (READ | (1 << BIO_RW_META))
 #define WRITE_SYNC      (WRITE | (1 << BIO_RW_SYNC))
+#define SWRITE_SYNC     (SWRITE | (1 << BIO_RW_SYNC))
 #define WRITE_BARRIER   ((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
 
 #define SEL_IN          1
@@ -894,8 +895,6 @@ static inline int file_check_writeable(struct file *filp)
 typedef struct files_struct *fl_owner_t;
 
 struct file_lock_operations {
-        void (*fl_insert)(struct file_lock *);  /* lock insertion callback */
-        void (*fl_remove)(struct file_lock *);  /* lock removal callback */
         void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
         void (*fl_release_private)(struct file_lock *);
 };
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index fb9af6a0fe9c..8dc730132192 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -171,7 +171,7 @@ struct i2c_client {
         struct i2c_adapter *adapter;    /* the adapter we sit on        */
         struct i2c_driver *driver;      /* and our access routines      */
         struct device dev;              /* the device structure         */
-        int irq;                        /* irq issued by device (or -1) */
+        int irq;                        /* irq issued by device         */
         struct list_head list;          /* DEPRECATED */
         struct completion released;
 };
diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index f1fbe9c930d7..d4efe4014705 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -41,7 +41,7 @@ struct ip_tunnel_prl {
         __u16                   __reserved;
         __u32                   datalen;
         __u32                   __reserved2;
-        void __user             *data;
+        /* data follows */
 };
 
 /* PRL flags */
diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h
index 80335b7d77c5..c4335faebb63 100644
--- a/include/linux/inet_lro.h
+++ b/include/linux/inet_lro.h
@@ -84,7 +84,11 @@ struct net_lro_mgr {
                                     from received packets and eth protocol
                                     is still ETH_P_8021Q */
 
-        u32 ip_summed;      /* Set in non generated SKBs in page mode */
+        /*
+         * Set for generated SKBs that are not added to
+         * the frag list in fragmented mode
+         */
+        u32 ip_summed;
         u32 ip_summed_aggr; /* Set in aggregated SKBs: CHECKSUM_UNNECESSARY
                              * or CHECKSUM_NONE */
 
diff --git a/include/linux/input.h b/include/linux/input.h
index e075c4b762fb..d150c57e5f0a 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -534,8 +534,8 @@ struct input_absinfo {
 
 #define KEY_FRAMEBACK           0x1b4   /* Consumer - transport controls */
 #define KEY_FRAMEFORWARD        0x1b5
-
 #define KEY_CONTEXT_MENU        0x1b6   /* GenDesc - system context menu */
+#define KEY_MEDIA_REPEAT        0x1b7   /* Consumer - transport control */
 
 #define KEY_DEL_EOL             0x1c0
 #define KEY_DEL_EOS             0x1c1
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 792bf0aa779b..2e70006c7fa8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -46,6 +46,9 @@ extern const char linux_proc_banner[];
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
 
+#define _RET_IP_                (unsigned long)__builtin_return_address(0)
+#define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
+
 #ifdef CONFIG_LBD
 # include <asm/div64.h>
 # define sector_div(a, b) do_div(a, b)
diff --git a/include/linux/ks0108.h b/include/linux/ks0108.h
index a2c54acceb4e..cb311798e0bc 100644
--- a/include/linux/ks0108.h
+++ b/include/linux/ks0108.h
@@ -4,7 +4,7 @@
  * Description: ks0108 LCD Controller driver header
  *     License: GPLv2
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 092b1b25291d..de9d1df4bba2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -33,6 +33,7 @@
 #define KVM_REQ_REPORT_TPR_ACCESS  2
 #define KVM_REQ_MMU_RELOAD         3
 #define KVM_REQ_TRIPLE_FAULT       4
+#define KVM_REQ_PENDING_TIMER      5
 
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f27fd2009334..25f87102ab66 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -88,6 +88,8 @@ struct wireless_dev;
 #define NETDEV_TX_BUSY 1        /* driver tx path was busy*/
 #define NETDEV_TX_LOCKED -1     /* driver tx lock was already taken */
 
+#ifdef  __KERNEL__
+
 /*
  *      Compute the worst case header length according to the protocols
  *      used.
@@ -114,6 +116,8 @@ struct wireless_dev;
 #define MAX_HEADER (LL_MAX_HEADER + 48)
 #endif
 
+#endif  /*  __KERNEL__  */
+
 struct net_device_subqueue
 {
         /* Give a control state for each queue.  This struct may contain
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f31debfac926..0d2a4e7012aa 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -157,6 +157,7 @@ PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
 __PAGEFLAG(Slab, slab)
 PAGEFLAG(Checked, owner_priv_1)         /* Used by some filesystems */
 PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */
+PAGEFLAG(SavePinned, dirty);                                    /* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
 PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
         __SETPAGEFLAG(Private, private)
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index eafc9d6d2b35..65953822c9cb 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1520,6 +1520,7 @@
 #define PCI_DEVICE_ID_MARVELL_GT64260   0x6430
 #define PCI_DEVICE_ID_MARVELL_MV64360   0x6460
 #define PCI_DEVICE_ID_MARVELL_MV64460   0x6480
+#define PCI_DEVICE_ID_MARVELL_CAFE_SD   0x4101
 
 #define PCI_VENDOR_ID_V3                0x11b0
 #define PCI_DEVICE_ID_V3_V960           0x0001
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
new file mode 100644
index 000000000000..bde4586f4382
--- /dev/null
+++ b/include/linux/rculist.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_RCULIST_H
+#define _LINUX_RCULIST_H
+
+#include <linux/list.h>
+
+#endif  /* _LINUX_RCULIST_H */
diff --git a/include/linux/resume-trace.h b/include/linux/resume-trace.h
index f3f4f28c6960..c9ba2fdf807d 100644
--- a/include/linux/resume-trace.h
+++ b/include/linux/resume-trace.h
@@ -8,7 +8,7 @@ extern int pm_trace_enabled;
 
 struct device;
 extern void set_trace_device(struct device *);
-extern void generate_resume_trace(void *tracedata, unsigned int user);
+extern void generate_resume_trace(const void *tracedata, unsigned int user);
 
 #define TRACE_DEVICE(dev) do { \
         if (pm_trace_enabled) \
diff --git a/include/linux/securebits.h b/include/linux/securebits.h
index c1f19dbceb05..92f09bdf1175 100644
--- a/include/linux/securebits.h
+++ b/include/linux/securebits.h
@@ -7,14 +7,15 @@
    inheritance of root-permissions and suid-root executable under
    compatibility mode. We raise the effective and inheritable bitmasks
    *of the executable file* if the effective uid of the new process is
-   0. If the real uid is 0, we raise the inheritable bitmask of the
+   0. If the real uid is 0, we raise the effective (legacy) bit of the
    executable file. */
 #define SECURE_NOROOT                   0
 #define SECURE_NOROOT_LOCKED            1  /* make bit-0 immutable */
 
-/* When set, setuid to/from uid 0 does not trigger capability-"fixes"
-   to be compatible with old programs relying on set*uid to loose
-   privileges. When unset, setuid doesn't change privileges. */
+/* When set, setuid to/from uid 0 does not trigger capability-"fixup".
+   When unset, to provide compatiblility with old programs relying on
+   set*uid to gain/lose privilege, transitions to/from uid 0 cause
+   capabilities to be gained/lost. */
 #define SECURE_NO_SETUID_FIXUP          2
 #define SECURE_NO_SETUID_FIXUP_LOCKED   3  /* make bit-2 immutable */
 
@@ -26,10 +27,10 @@
 #define SECURE_KEEP_CAPS                4
 #define SECURE_KEEP_CAPS_LOCKED         5  /* make bit-4 immutable */
 
-/* Each securesetting is implemented using two bits. One bit specify
+/* Each securesetting is implemented using two bits. One bit specifies
    whether the setting is on or off. The other bit specify whether the
-   setting is fixed or not. A setting which is fixed cannot be changed
-   from user-level. */
+   setting is locked or not. A setting which is locked cannot be
+   changed from user-level. */
 #define issecure_mask(X)        (1 << (X))
 #define issecure(X)             (issecure_mask(X) & current->securebits)
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c2ad35016599..9aa90a6f20e0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -1,7 +1,7 @@
 /*
  * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
  *
- * (C) SGI 2006, Christoph Lameter <clameter@sgi.com>
+ * (C) SGI 2006, Christoph Lameter
  *      Cleaned up and restructured to ease the addition of alternative
  *      implementations of SLAB allocators.
  */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 71e43a12ebbb..d117ea2825a9 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -4,7 +4,7 @@
 /*
  * SLUB : A Slab allocator without object queues.
  *
- * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 SGI, Christoph Lameter
  */
 #include <linux/types.h>
 #include <linux/gfp.h>
@@ -137,10 +137,12 @@ static __always_inline int kmalloc_index(size_t size)
         if (size <= KMALLOC_MIN_SIZE)
                 return KMALLOC_SHIFT_LOW;
 
+#if KMALLOC_MIN_SIZE <= 64
         if (size > 64 && size <= 96)
                 return 1;
         if (size > 128 && size <= 192)
                 return 2;
+#endif
         if (size <=          8) return 3;
         if (size <=         16) return 4;
         if (size <=         32) return 5;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 06d3e6eb9ca8..917707e6151d 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -66,8 +66,7 @@ struct thermal_cooling_device {
                                 ((long)t-2732+5)/10 : ((long)t-2732-5)/10)
 #define CELSIUS_TO_KELVIN(t)    ((t)*10+2732)
 
-#if defined(CONFIG_HWMON) ||    \
-        (defined(CONFIG_HWMON_MODULE) && defined(CONFIG_THERMAL_MODULE))
+#if defined(CONFIG_THERMAL_HWMON)
 /* thermal zone devices with the same type share one hwmon device */
 struct thermal_hwmon_device {
         char type[THERMAL_NAME_LENGTH];
@@ -94,8 +93,7 @@ struct thermal_zone_device {
         struct idr idr;
         struct mutex lock;      /* protect cooling devices list */
         struct list_head node;
-#if defined(CONFIG_HWMON) ||    \
-        (defined(CONFIG_HWMON_MODULE) && defined(CONFIG_THERMAL_MODULE))
+#if defined(CONFIG_THERMAL_HWMON)
         struct list_head hwmon_node;
         struct thermal_hwmon_device *hwmon;
         struct thermal_hwmon_attr temp_input;   /* hwmon sys attr */
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 59f1c0bd8f9c..d2a003586761 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -27,8 +27,7 @@
  *      This routine is called by the kernel to write a series of
  *      characters to the tty device.  The characters may come from
  *      user space or kernel space.  This routine will return the
- *      number of characters actually accepted for writing.  This
- *      routine is mandatory.
+ *      number of characters actually accepted for writing.
  *
  *      Optional: Required for writable devices.
  *
@@ -134,7 +133,7 @@
  *      This routine notifies the tty driver that it should hangup the
  *      tty device.
  *
- *      Required:
+ *      Optional:
  *
  * void (*break_ctl)(struct tty_stuct *tty, int state);
  *
diff --git a/include/media/cx25840.h b/include/media/cx25840.h
index cd599ad29fb2..db431d513f2f 100644
--- a/include/media/cx25840.h
+++ b/include/media/cx25840.h
@@ -32,12 +32,16 @@ enum cx25840_video_input {
         CX25840_COMPOSITE7,
         CX25840_COMPOSITE8,
 
-        /* S-Video inputs consist of one luma input (In1-In4) ORed with one
+        /* S-Video inputs consist of one luma input (In1-In8) ORed with one
            chroma input (In5-In8) */
         CX25840_SVIDEO_LUMA1 = 0x10,
         CX25840_SVIDEO_LUMA2 = 0x20,
         CX25840_SVIDEO_LUMA3 = 0x30,
         CX25840_SVIDEO_LUMA4 = 0x40,
+        CX25840_SVIDEO_LUMA5 = 0x50,
+        CX25840_SVIDEO_LUMA6 = 0x60,
+        CX25840_SVIDEO_LUMA7 = 0x70,
+        CX25840_SVIDEO_LUMA8 = 0x80,
         CX25840_SVIDEO_CHROMA4 = 0x400,
         CX25840_SVIDEO_CHROMA5 = 0x500,
         CX25840_SVIDEO_CHROMA6 = 0x600,
diff --git a/include/media/ir-common.h b/include/media/ir-common.h
index bfee8be5d63f..b8e8aa91905a 100644
--- a/include/media/ir-common.h
+++ b/include/media/ir-common.h
@@ -146,6 +146,7 @@ extern IR_KEYTAB_TYPE ir_codes_behold_columbus[IR_KEYTAB_SIZE];
 extern IR_KEYTAB_TYPE ir_codes_pinnacle_pctv_hd[IR_KEYTAB_SIZE];
 extern IR_KEYTAB_TYPE ir_codes_genius_tvgo_a11mce[IR_KEYTAB_SIZE];
 extern IR_KEYTAB_TYPE ir_codes_powercolor_real_angel[IR_KEYTAB_SIZE];
+extern IR_KEYTAB_TYPE ir_codes_avermedia_a16d[IR_KEYTAB_SIZE];
 
 #endif
 
diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h
index 33f01ae08f76..859f7a6f6f67 100644
--- a/include/media/v4l2-dev.h
+++ b/include/media/v4l2-dev.h
@@ -40,9 +40,9 @@
 #define VFL_TYPE_VTX            3
 
 /*  Video standard functions  */
-extern char *v4l2_norm_to_name(v4l2_std_id id);
+extern const char *v4l2_norm_to_name(v4l2_std_id id);
 extern int v4l2_video_std_construct(struct v4l2_standard *vs,
-                                    int id, char *name);
+                                    int id, const char *name);
 /* Prints the ioctl in a human-readable format */
 extern void v4l_printk_ioctl(unsigned int cmd);
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e0a612bc9c4e..f422f7218e1c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -367,6 +367,12 @@ static inline int ipv6_addr_any(const struct in6_addr *a)
                  a->s6_addr32[2] | a->s6_addr32[3] ) == 0); 
 }
 
+static inline int ipv6_addr_loopback(const struct in6_addr *a)
+{
+        return ((a->s6_addr32[0] | a->s6_addr32[1] |
+                 a->s6_addr32[2] | (a->s6_addr32[3] ^ htonl(1))) == 0);
+}
+
 static inline int ipv6_addr_v4mapped(const struct in6_addr *a)
 {
         return ((a->s6_addr32[0] | a->s6_addr32[1] |
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index dae3f9ec1154..bcd1623245cb 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -595,6 +595,15 @@ enum ieee80211_key_alg {
         ALG_CCMP,
 };
 
+/**
+ * enum ieee80211_key_len - key length
+ * @WEP40: WEP 5 byte long key
+ * @WEP104: WEP 13 byte long key
+ */
+enum ieee80211_key_len {
+        LEN_WEP40 = 5,
+        LEN_WEP104 = 13,
+};
 
 /**
  * enum ieee80211_key_flags - key flags
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index aa540e6be502..d9dd0f707296 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -95,6 +95,11 @@ extern struct list_head net_namespace_list;
 #ifdef CONFIG_NET_NS
 extern void __put_net(struct net *net);
 
+static inline int net_alive(struct net *net)
+{
+        return net && atomic_read(&net->count);
+}
+
 static inline struct net *get_net(struct net *net)
 {
         atomic_inc(&net->count);
@@ -125,6 +130,12 @@ int net_eq(const struct net *net1, const struct net *net2)
         return net1 == net2;
 }
 #else
+
+static inline int net_alive(struct net *net)
+{
+        return 1;
+}
+
 static inline struct net *get_net(struct net *net)
 {
         return net;
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index f736e842977f..f80c0ed6d870 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -15,6 +15,7 @@ enum nf_ct_ext_id
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
+        struct rcu_head rcu;
         u8 offset[NF_CT_EXT_NUM];
         u8 len;
         char data[0];
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ab502ec1c61c..a87fc0312edc 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -178,7 +178,7 @@ extern struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops);
 extern struct Qdisc *qdisc_create_dflt(struct net_device *dev,
                                        struct Qdisc_ops *ops, u32 parentid);
 extern void tcf_destroy(struct tcf_proto *tp);
-extern void tcf_destroy_chain(struct tcf_proto *fl);
+extern void tcf_destroy_chain(struct tcf_proto **fl);
 
 static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
                                        struct sk_buff_head *list)
diff --git a/include/xen/events.h b/include/xen/events.h
index acd8e062c85f..67c4436554a9 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -32,6 +32,7 @@ void unbind_from_irqhandler(unsigned int irq, void *dev_id);
 
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector);
 int resend_irq_on_evtchn(unsigned int irq);
+void rebind_evtchn_irq(int evtchn, int irq);
 
 static inline void notify_remote_via_evtchn(int port)
 {
@@ -40,4 +41,7 @@ static inline void notify_remote_via_evtchn(int port)
 }
 
 extern void notify_remote_via_irq(int irq);
+
+extern void xen_irq_resume(void);
+
 #endif  /* _XEN_EVENTS_H */
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 466204846121..a40f1cd91be1 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -51,6 +51,9 @@ struct gnttab_free_callback {
         u16 count;
 };
 
+int gnttab_suspend(void);
+int gnttab_resume(void);
+
 int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
                                 int readonly);
 
diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h
index 21c0ecfd786d..98b79bc404dd 100644
--- a/include/xen/hvc-console.h
+++ b/include/xen/hvc-console.h
@@ -3,4 +3,13 @@
 
 extern struct console xenboot_console;
 
+#ifdef CONFIG_HVC_XEN
+void xen_console_resume(void);
+#else
+static inline void xen_console_resume(void) { }
+#endif
+
+void xen_raw_console_write(const char *str);
+void xen_raw_printk(const char *fmt, ...);
+
 #endif  /* XEN_HVC_CONSOLE_H */
diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h
index a64d3df5bd95..7a8262c375cc 100644
--- a/include/xen/interface/elfnote.h
+++ b/include/xen/interface/elfnote.h
@@ -120,6 +120,26 @@
  */
 #define XEN_ELFNOTE_BSD_SYMTAB    11
 
+/*
+ * The lowest address the hypervisor hole can begin at (numeric).
+ *
+ * This must not be set higher than HYPERVISOR_VIRT_START. Its presence
+ * also indicates to the hypervisor that the kernel can deal with the
+ * hole starting at a higher address.
+ */
+#define XEN_ELFNOTE_HV_START_LOW  12
+
+/*
+ * List of maddr_t-sized mask/value pairs describing how to recognize
+ * (non-present) L1 page table entries carrying valid MFNs (numeric).
+ */
+#define XEN_ELFNOTE_L1_MFN_VALID  13
+
+/*
+ * Whether or not the guest supports cooperative suspend cancellation.
+ */
+#define XEN_ELFNOTE_SUSPEND_CANCEL 14
+
 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */
 
 /*
diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
index d73228d16488..f51b6413b054 100644
--- a/include/xen/interface/features.h
+++ b/include/xen/interface/features.h
@@ -38,6 +38,9 @@
  */
 #define XENFEAT_pae_pgdir_above_4gb        4
 
+/* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */
+#define XENFEAT_mmu_pt_update_preserve_ad  5
+
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */
diff --git a/include/xen/interface/io/fbif.h b/include/xen/interface/io/fbif.h
index 5a934dd7796d..974a51ed9165 100644
--- a/include/xen/interface/io/fbif.h
+++ b/include/xen/interface/io/fbif.h
@@ -49,11 +49,27 @@ struct xenfb_update {
         int32_t height;         /* rect height */
 };
 
+/*
+ * Framebuffer resize notification event
+ * Capable backend sets feature-resize in xenstore.
+ */
+#define XENFB_TYPE_RESIZE 3
+
+struct xenfb_resize {
+        uint8_t type;           /* XENFB_TYPE_RESIZE */
+        int32_t width;          /* width in pixels */
+        int32_t height;         /* height in pixels */
+        int32_t stride;         /* stride in bytes */
+        int32_t depth;          /* depth in bits */
+        int32_t offset;         /* start offset within framebuffer */
+};
+
 #define XENFB_OUT_EVENT_SIZE 40
 
 union xenfb_out_event {
         uint8_t type;
         struct xenfb_update update;
+        struct xenfb_resize resize;
         char pad[XENFB_OUT_EVENT_SIZE];
 };
 
@@ -105,15 +121,18 @@ struct xenfb_page {
          * Each directory page holds PAGE_SIZE / sizeof(*pd)
          * framebuffer pages, and can thus map up to PAGE_SIZE *
          * PAGE_SIZE / sizeof(*pd) bytes.  With PAGE_SIZE == 4096 and
-         * sizeof(unsigned long) == 4, that's 4 Megs.  Two directory
-         * pages should be enough for a while.
+         * sizeof(unsigned long) == 4/8, that's 4 Megs 32 bit and 2
+         * Megs 64 bit.  256 directories give enough room for a 512
+         * Meg framebuffer with a max resolution of 12,800x10,240.
+         * Should be enough for a while with room leftover for
+         * expansion.
          */
-        unsigned long pd[2];
+        unsigned long pd[256];
 };
 
 /*
- * Wart: xenkbd needs to know resolution.  Put it here until a better
- * solution is found, but don't leak it to the backend.
+ * Wart: xenkbd needs to know default resolution.  Put it here until a
+ * better solution is found, but don't leak it to the backend.
  */
 #ifdef __KERNEL__
 #define XENFB_WIDTH 800
diff --git a/include/xen/interface/io/kbdif.h b/include/xen/interface/io/kbdif.h
index fb97f4284ffd..8066c7849fbe 100644
--- a/include/xen/interface/io/kbdif.h
+++ b/include/xen/interface/io/kbdif.h
@@ -49,6 +49,7 @@ struct xenkbd_motion {
         uint8_t type;           /* XENKBD_TYPE_MOTION */
         int32_t rel_x;          /* relative X motion */
         int32_t rel_y;          /* relative Y motion */
+        int32_t rel_z;          /* relative Z motion (wheel) */
 };
 
 struct xenkbd_key {
@@ -61,6 +62,7 @@ struct xenkbd_position {
         uint8_t type;           /* XENKBD_TYPE_POS */
         int32_t abs_x;          /* absolute X position (in FB pixels) */
         int32_t abs_y;          /* absolute Y position (in FB pixels) */
+        int32_t rel_z;          /* relative Z motion (wheel) */
 };
 
 #define XENKBD_IN_EVENT_SIZE 40
diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h
index da768469aa92..af36ead16817 100644
--- a/include/xen/interface/memory.h
+++ b/include/xen/interface/memory.h
@@ -29,7 +29,7 @@ struct xen_memory_reservation {
      *   OUT: GMFN bases of extents that were allocated
      *   (NB. This command also updates the mach_to_phys translation table)
      */
-    ulong extent_start;
+    GUEST_HANDLE(ulong) extent_start;
 
     /* Number of extents, and size/alignment of each (2^extent_order pages). */
     unsigned long  nr_extents;
@@ -50,6 +50,7 @@ struct xen_memory_reservation {
     domid_t        domid;
 
 };
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation);
 
 /*
  * Returns the maximum machine frame number of mapped RAM in this system.
@@ -85,7 +86,7 @@ struct xen_machphys_mfn_list {
      * any large discontiguities in the machine address space, 2MB gaps in
      * the machphys table will be represented by an MFN base of zero.
      */
-    ulong extent_start;
+    GUEST_HANDLE(ulong) extent_start;
 
     /*
      * Number of extents written to the above array. This will be smaller
@@ -93,6 +94,7 @@ struct xen_machphys_mfn_list {
      */
     unsigned int nr_extents;
 };
+DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mfn_list);
 
 /*
  * Sets the GPFN at which a particular page appears in the specified guest's
@@ -115,6 +117,7 @@ struct xen_add_to_physmap {
     /* GPFN where the source mapping page should appear. */
     unsigned long gpfn;
 };
+DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap);
 
 /*
  * Translates a list of domain-specific GPFNs into MFNs. Returns a -ve error
@@ -129,13 +132,14 @@ struct xen_translate_gpfn_list {
     unsigned long nr_gpfns;
 
     /* List of GPFNs to translate. */
-    ulong gpfn_list;
+    GUEST_HANDLE(ulong) gpfn_list;
 
     /*
      * Output list to contain MFN translations. May be the same as the input
      * list (in which case each input GPFN is overwritten with the output MFN).
      */
-    ulong mfn_list;
+    GUEST_HANDLE(ulong) mfn_list;
 };
+DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list);
 
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 9b018da48cf3..2befa3e2f1bc 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -10,6 +10,7 @@
 #define __XEN_PUBLIC_XEN_H__
 
 #include <asm/xen/interface.h>
+#include <asm/pvclock-abi.h>
 
 /*
  * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
@@ -113,9 +114,14 @@
  * ptr[:2]  -- Machine address within the frame whose mapping to modify.
  *             The frame must belong to the FD, if one is specified.
  * val      -- Value to write into the mapping entry.
+ *
+ * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
+ * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
+ * with those in @val.
  */
-#define MMU_NORMAL_PT_UPDATE     0 /* checked '*ptr = val'. ptr is MA.       */
-#define MMU_MACHPHYS_UPDATE      1 /* ptr = MA of frame to modify entry for  */
+#define MMU_NORMAL_PT_UPDATE      0 /* checked '*ptr = val'. ptr is MA.       */
+#define MMU_MACHPHYS_UPDATE       1 /* ptr = MA of frame to modify entry for  */
+#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
 
 /*
  * MMU EXTENDED OPERATIONS
@@ -336,7 +342,7 @@ struct vcpu_info {
         uint8_t evtchn_upcall_mask;
         unsigned long evtchn_pending_sel;
         struct arch_vcpu_info arch;
-        struct vcpu_time_info time;
+        struct pvclock_vcpu_time_info time;
 }; /* 64 bytes (x86) */
 
 /*
@@ -384,9 +390,7 @@ struct shared_info {
          * Wallclock time: updated only by control software. Guests should base
          * their gettimeofday() syscall on this wallclock-base value.
          */
-        uint32_t wc_version;      /* Version counter: see vcpu_time_info_t. */
-        uint32_t wc_sec;          /* Secs  00:00:00 UTC, Jan 1, 1970.  */
-        uint32_t wc_nsec;         /* Nsecs 00:00:00 UTC, Jan 1, 1970.  */
+        struct pvclock_wall_clock wc;
 
         struct arch_shared_info arch;
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 10ddfe0142d0..a706d6a78960 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,4 +5,10 @@
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
+void xen_pre_suspend(void);
+void xen_post_suspend(int suspend_cancelled);
+
+void xen_mm_pin_all(void);
+void xen_mm_unpin_all(void);
+
 #endif /* INCLUDE_XEN_OPS_H */