28 files changed, 172 insertions, 148 deletions

diff --git a/include/asm-x86_64/apicdef.h b/include/asm-x86_64/apicdef.h
index decaa2d540e8..5a48e9bcf218 100644
--- a/include/asm-x86_64/apicdef.h
+++ b/include/asm-x86_64/apicdef.h
@@ -39,6 +39,7 @@
 #define                 APIC_SPIV_FOCUS_DISABLED        (1<<9)
 #define                 APIC_SPIV_APIC_ENABLED          (1<<8)
 #define         APIC_ISR        0x100
+#define         APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
 #define         APIC_TMR        0x180
 #define         APIC_IRR        0x200
 #define         APIC_ESR        0x280
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index 4b5cd553e772..cecbf7baa6aa 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
 ({                                                              \
         int c, old;                                             \
         c = atomic_read(v);                                     \
-        while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+        for (;;) {                                              \
+                if (unlikely(c == (u)))                         \
+                        break;                                  \
+                old = atomic_cmpxchg((v), c, c + (a));          \
+                if (likely(old == c))                           \
+                        break;                                  \
                 c = old;                                        \
+        }                                                       \
         c != (u);                                               \
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h
index eb4df23e1e41..79212128d0f7 100644
--- a/include/asm-x86_64/bitops.h
+++ b/include/asm-x86_64/bitops.h
@@ -356,14 +356,7 @@ static __inline__ unsigned long __fls(unsigned long word)
 
 #ifdef __KERNEL__
 
-static inline int sched_find_first_bit(const unsigned long *b)
-{
-        if (b[0])
-                return __ffs(b[0]);
-        if (b[1])
-                return __ffs(b[1]) + 64;
-        return __ffs(b[2]) + 128;
-}
+#include <asm-generic/bitops/sched.h>
 
 /**
  * ffs - find first bit set
@@ -412,43 +405,20 @@ static __inline__ int fls(int x)
         return r+1;
 }
 
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-#define hweight64(x) generic_hweight64(x)
-#define hweight32(x) generic_hweight32(x)
-#define hweight16(x) generic_hweight16(x)
-#define hweight8(x) generic_hweight8(x)
+#include <asm-generic/bitops/hweight.h>
 
 #endif /* __KERNEL__ */
 
 #ifdef __KERNEL__
 
-#define ext2_set_bit(nr,addr) \
-        __test_and_set_bit((nr),(unsigned long*)addr)
+#include <asm-generic/bitops/ext2-non-atomic.h>
+
 #define ext2_set_bit_atomic(lock,nr,addr) \
                 test_and_set_bit((nr),(unsigned long*)addr)
-#define ext2_clear_bit(nr, addr) \
-        __test_and_clear_bit((nr),(unsigned long*)addr)
 #define ext2_clear_bit_atomic(lock,nr,addr) \
                 test_and_clear_bit((nr),(unsigned long*)addr)
-#define ext2_test_bit(nr, addr)      test_bit((nr),(unsigned long*)addr)
-#define ext2_find_first_zero_bit(addr, size) \
-        find_first_zero_bit((unsigned long*)addr, size)
-#define ext2_find_next_zero_bit(addr, size, off) \
-        find_next_zero_bit((unsigned long*)addr, size, off)
-
-/* Bitmap functions for the minix filesystem.  */
-#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,(void*)addr)
-#define minix_set_bit(nr,addr) __set_bit(nr,(void*)addr)
-#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,(void*)addr)
-#define minix_test_bit(nr,addr) test_bit(nr,(void*)addr)
-#define minix_find_first_zero_bit(addr,size) \
-        find_first_zero_bit((void*)addr,size)
+
+#include <asm-generic/bitops/minix.h>
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-x86_64/cache.h b/include/asm-x86_64/cache.h
index 263f0a211ed7..c8043a16152e 100644
--- a/include/asm-x86_64/cache.h
+++ b/include/asm-x86_64/cache.h
@@ -20,6 +20,8 @@
        __attribute__((__section__(".data.page_aligned")))
 #endif
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/dmi.h b/include/asm-x86_64/dmi.h
new file mode 100644
index 000000000000..93b2b15d4325
--- /dev/null
+++ b/include/asm-x86_64/dmi.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_DMI_H
+#define _ASM_DMI_H 1
+
+#include <asm/io.h>
+
+extern void *dmi_ioremap(unsigned long addr, unsigned long size);
+extern void dmi_iounmap(void *addr, unsigned long size);
+
+#define DMI_MAX_DATA 2048
+
+extern int dmi_alloc_index;
+extern char dmi_alloc_data[DMI_MAX_DATA];
+
+/* This is so early that there is no good way to allocate dynamic memory. 
+   Allocate data in an BSS array. */
+static inline void *dmi_alloc(unsigned len)
+{
+        int idx = dmi_alloc_index;
+        if ((dmi_alloc_index += len) > DMI_MAX_DATA)
+                return NULL;
+        return dmi_alloc_data + idx;
+}
+
+#define dmi_ioremap early_ioremap
+#define dmi_iounmap early_iounmap
+
+#endif
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
index 43862cd6a569..c98633af07d2 100644
--- a/include/asm-x86_64/elf.h
+++ b/include/asm-x86_64/elf.h
@@ -8,6 +8,7 @@
 #include <asm/ptrace.h>
 #include <asm/user.h>
 #include <asm/processor.h>
+#include <asm/compat.h>
 
 /* x86-64 relocation types */
 #define R_X86_64_NONE           0       /* No reloc */
@@ -157,6 +158,9 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
 #define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
 #define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
 
+/* 1GB for 64bit, 8MB for 32bit */
+#define STACK_RND_MASK (is_compat_task() ? 0x7ff : 0x3fffff)
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/floppy.h b/include/asm-x86_64/floppy.h
index af7ded63b517..52825ce689f2 100644
--- a/include/asm-x86_64/floppy.h
+++ b/include/asm-x86_64/floppy.h
@@ -155,7 +155,7 @@ static int fd_request_irq(void)
 
 static unsigned long dma_mem_alloc(unsigned long size)
 {
-        return __get_dma_pages(GFP_KERNEL,get_order(size));
+        return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY,get_order(size));
 }
 
 
diff --git a/include/asm-x86_64/futex.h b/include/asm-x86_64/futex.h
index 8602c09bf89e..9804bf07b092 100644
--- a/include/asm-x86_64/futex.h
+++ b/include/asm-x86_64/futex.h
@@ -94,5 +94,32 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
         return ret;
 }
 
+static inline int
+futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+{
+        if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+                return -EFAULT;
+
+        __asm__ __volatile__(
+                "1:     " LOCK_PREFIX "cmpxchgl %3, %1          \n"
+
+                "2:     .section .fixup, \"ax\"                 \n"
+                "3:     mov     %2, %0                          \n"
+                "       jmp     2b                              \n"
+                "       .previous                               \n"
+
+                "       .section __ex_table, \"a\"              \n"
+                "       .align  8                               \n"
+                "       .quad   1b,3b                           \n"
+                "       .previous                               \n"
+
+                : "=a" (oldval), "=m" (*uaddr)
+                : "i" (-EFAULT), "r" (newval), "0" (oldval)
+                : "memory"
+        );
+
+        return oldval;
+}
+
 #endif
 #endif
diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h
index 9dac18db8291..cafdfb37f0d8 100644
--- a/include/asm-x86_64/io.h
+++ b/include/asm-x86_64/io.h
@@ -135,6 +135,9 @@ static inline void __iomem * ioremap (unsigned long offset, unsigned long size)
         return __ioremap(offset, size, 0);
 }
 
+extern void *early_ioremap(unsigned long addr, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+
 /*
  * This one maps high address device memory and turns off caching for that area.
  * it's useful if some control registers are in such an area and write combining
@@ -143,11 +146,6 @@ static inline void __iomem * ioremap (unsigned long offset, unsigned long size)
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
 extern void iounmap(volatile void __iomem *addr);
 
-/* Use normal IO mappings for DMI */
-#define dmi_ioremap ioremap
-#define dmi_iounmap(x,l) iounmap(x)
-#define dmi_alloc(l) kmalloc(l, GFP_ATOMIC)
-
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
@@ -202,23 +200,6 @@ static inline __u64 __readq(const volatile void __iomem *addr)
 
 #define mmiowb()
 
-#ifdef CONFIG_UNORDERED_IO
-static inline void __writel(__u32 val, volatile void __iomem *addr)
-{
-        volatile __u32 __iomem *target = addr;
-        asm volatile("movnti %1,%0"
-                     : "=m" (*target)
-                     : "r" (val) : "memory");
-}
-
-static inline void __writeq(__u64 val, volatile void __iomem *addr)
-{
-        volatile __u64 __iomem *target = addr;
-        asm volatile("movnti %1,%0"
-                     : "=m" (*target)
-                     : "r" (val) : "memory");
-}
-#else
 static inline void __writel(__u32 b, volatile void __iomem *addr)
 {
         *(__force volatile __u32 *)addr = b;
@@ -227,7 +208,6 @@ static inline void __writeq(__u64 b, volatile void __iomem *addr)
 {
         *(__force volatile __u64 *)addr = b;
 }
-#endif
 static inline void __writeb(__u8 b, volatile void __iomem *addr)
 {
         *(__force volatile __u8 *)addr = b;
@@ -269,23 +249,11 @@ void memset_io(volatile void __iomem *a, int b, size_t c);
  */
 #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
 
-#define isa_readb(a) readb(__ISA_IO_base + (a))
-#define isa_readw(a) readw(__ISA_IO_base + (a))
-#define isa_readl(a) readl(__ISA_IO_base + (a))
-#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
-#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
-#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
-#define isa_memset_io(a,b,c)            memset_io(__ISA_IO_base + (a),(b),(c))
-#define isa_memcpy_fromio(a,b,c)        memcpy_fromio((a),__ISA_IO_base + (b),(c))
-#define isa_memcpy_toio(a,b,c)          memcpy_toio(__ISA_IO_base + (a),(b),(c))
-
-
 /*
  * Again, x86-64 does not require mem IO specific function.
  */
 
 #define eth_io_copy_and_sum(a,b,c,d)            eth_copy_and_sum((a),(void *)(b),(c),(d))
-#define isa_eth_io_copy_and_sum(a,b,c,d)        eth_copy_and_sum((a),(void *)(__ISA_IO_base + (b)),(c),(d))
 
 /**
  *      check_signature         -       find BIOS signatures
diff --git a/include/asm-x86_64/kdebug.h b/include/asm-x86_64/kdebug.h
index b9ed4c0c8783..cf795631d9b4 100644
--- a/include/asm-x86_64/kdebug.h
+++ b/include/asm-x86_64/kdebug.h
@@ -5,21 +5,20 @@
 
 struct pt_regs;
 
-struct die_args { 
+struct die_args {
         struct pt_regs *regs;
         const char *str;
-        long err; 
+        long err;
         int trapnr;
         int signr;
-}; 
+};
+
+extern int register_die_notifier(struct notifier_block *);
+extern int unregister_die_notifier(struct notifier_block *);
+extern struct atomic_notifier_head die_chain;
 
-/* Note - you should never unregister because that can race with NMIs.
-   If you really want to do it first unregister - then synchronize_sched - then free.
-  */
-int register_die_notifier(struct notifier_block *nb);
-extern struct notifier_block *die_chain;
 /* Grossly misnamed. */
-enum die_val { 
+enum die_val {
         DIE_OOPS = 1,
         DIE_INT3,
         DIE_DEBUG,
@@ -33,8 +32,8 @@ enum die_val {
         DIE_CALL,
         DIE_NMI_IPI,
         DIE_PAGE_FAULT,
-}; 
-        
+};
+
 static inline int notify_die(enum die_val val, const char *str,
                         struct pt_regs *regs, long err, int trap, int sig)
 {
@@ -45,7 +44,7 @@ static inline int notify_die(enum die_val val, const char *str,
                 .trapnr = trap,
                 .signr = sig
         };
-        return notifier_call_chain(&die_chain, val, &args); 
+        return atomic_notifier_call_chain(&die_chain, val, &args);
 } 
 
 extern int printk_address(unsigned long address);
diff --git a/include/asm-x86_64/local.h b/include/asm-x86_64/local.h
index 3e72c41727c5..cd17945bf218 100644
--- a/include/asm-x86_64/local.h
+++ b/include/asm-x86_64/local.h
@@ -5,7 +5,7 @@
 
 typedef struct
 {
-        volatile unsigned int counter;
+        volatile long counter;
 } local_t;
 
 #define LOCAL_INIT(i)   { (i) }
@@ -13,34 +13,34 @@ typedef struct
 #define local_read(v)   ((v)->counter)
 #define local_set(v,i)  (((v)->counter) = (i))
 
-static __inline__ void local_inc(local_t *v)
+static inline void local_inc(local_t *v)
 {
         __asm__ __volatile__(
-                "incl %0"
+                "incq %0"
                 :"=m" (v->counter)
                 :"m" (v->counter));
 }
 
-static __inline__ void local_dec(local_t *v)
+static inline void local_dec(local_t *v)
 {
         __asm__ __volatile__(
-                "decl %0"
+                "decq %0"
                 :"=m" (v->counter)
                 :"m" (v->counter));
 }
 
-static __inline__ void local_add(unsigned int i, local_t *v)
+static inline void local_add(long i, local_t *v)
 {
         __asm__ __volatile__(
-                "addl %1,%0"
+                "addq %1,%0"
                 :"=m" (v->counter)
                 :"ir" (i), "m" (v->counter));
 }
 
-static __inline__ void local_sub(unsigned int i, local_t *v)
+static inline void local_sub(long i, local_t *v)
 {
         __asm__ __volatile__(
-                "subl %1,%0"
+                "subq %1,%0"
                 :"=m" (v->counter)
                 :"ir" (i), "m" (v->counter));
 }
diff --git a/include/asm-x86_64/mmu_context.h b/include/asm-x86_64/mmu_context.h
index 16e4be4de0c5..19f0c83d0792 100644
--- a/include/asm-x86_64/mmu_context.h
+++ b/include/asm-x86_64/mmu_context.h
@@ -34,12 +34,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
         unsigned cpu = smp_processor_id();
         if (likely(prev != next)) {
                 /* stop flush ipis for the previous mm */
-                clear_bit(cpu, &prev->cpu_vm_mask);
+                cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
                 write_pda(mmu_state, TLBSTATE_OK);
                 write_pda(active_mm, next);
 #endif
-                set_bit(cpu, &next->cpu_vm_mask);
+                cpu_set(cpu, next->cpu_vm_mask);
                 load_cr3(next->pgd);
 
                 if (unlikely(next->context.ldt != prev->context.ldt)) 
@@ -50,7 +50,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                 write_pda(mmu_state, TLBSTATE_OK);
                 if (read_pda(active_mm) != next)
                         out_of_line_bug();
-                if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
+                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
                         /* We were in lazy tlb mode and leave_mm disabled 
                          * tlb flush IPI delivery. We must reload CR3
                          * to make sure to use no freed page tables.
diff --git a/include/asm-x86_64/mmzone.h b/include/asm-x86_64/mmzone.h
index 972c9359f7d7..6b18cd8f293d 100644
--- a/include/asm-x86_64/mmzone.h
+++ b/include/asm-x86_64/mmzone.h
@@ -15,8 +15,13 @@
 #define NODEMAPSIZE 0xfff
 
 /* Simple perfect hash to map physical addresses to node numbers */
-extern int memnode_shift; 
-extern u8  memnodemap[NODEMAPSIZE]; 
+struct memnode {
+        int shift;
+        u8 map[NODEMAPSIZE];
+} ____cacheline_aligned;
+extern struct memnode memnode;
+#define memnode_shift memnode.shift
+#define memnodemap memnode.map
 
 extern struct pglist_data *node_data[];
 
@@ -39,12 +44,8 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
 #define pfn_to_nid(pfn) phys_to_nid((unsigned long)(pfn) << PAGE_SHIFT)
 #define kvaddr_to_nid(kaddr)    phys_to_nid(__pa(kaddr))
 
-extern struct page *pfn_to_page(unsigned long pfn);
-extern unsigned long page_to_pfn(struct page *page);
 extern int pfn_valid(unsigned long pfn);
 #endif
 
-#define local_mapnr(kvaddr) \
-        ( (__pa(kvaddr) >> PAGE_SHIFT) - node_start_pfn(kvaddr_to_nid(kvaddr)) )
 #endif
 #endif
diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h
index dffe276ca2df..f6cbb4cbb5a3 100644
--- a/include/asm-x86_64/numa.h
+++ b/include/asm-x86_64/numa.h
@@ -4,11 +4,11 @@
 #include <linux/nodemask.h>
 #include <asm/numnodes.h>
 
-struct node { 
+struct bootnode {
         u64 start,end; 
 };
 
-extern int compute_hash_shift(struct node *nodes, int numnodes);
+extern int compute_hash_shift(struct bootnode *nodes, int numnodes);
 extern int pxm_to_node(int nid);
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h
index 615e3e494929..408185bac351 100644
--- a/include/asm-x86_64/page.h
+++ b/include/asm-x86_64/page.h
@@ -123,8 +123,6 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define __boot_va(x)            __va(x)
 #define __boot_pa(x)            __pa(x)
 #ifdef CONFIG_FLATMEM
-#define pfn_to_page(pfn)        (mem_map + (pfn))
-#define page_to_pfn(page)       ((unsigned long)((page) - mem_map))
 #define pfn_valid(pfn)          ((pfn) < end_pfn)
 #endif
 
@@ -140,6 +138,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 
 #endif /* __KERNEL__ */
 
+#include <asm-generic/memory_model.h>
 #include <asm-generic/page.h>
 
 #endif /* _X86_64_PAGE_H */
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index c7ab38a601af..b47c3df9ed1d 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -22,8 +22,8 @@ struct x8664_pda {
         int nodenumber;             /* number of current node */
         unsigned int __softirq_pending;
         unsigned int __nmi_count;       /* number of NMI on this CPUs */
-        struct mm_struct *active_mm;
         int mmu_state;     
+        struct mm_struct *active_mm;
         unsigned apic_timer_irqs;
 } ____cacheline_aligned_in_smp;
 
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 29a6b0408f75..4405b4adeaba 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -26,10 +26,9 @@
 #define percpu_modcopy(pcpudst, src, size)                      \
 do {                                                            \
         unsigned int __i;                                       \
-        for (__i = 0; __i < NR_CPUS; __i++)                     \
-                if (cpu_possible(__i))                          \
-                        memcpy((pcpudst)+__per_cpu_offset(__i), \
-                               (src), (size));                  \
+        for_each_cpu(__i)                                       \
+                memcpy((pcpudst)+__per_cpu_offset(__i),         \
+                       (src), (size));                          \
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/asm-x86_64/pgalloc.h b/include/asm-x86_64/pgalloc.h
index 08cad2482bcb..43d4c333a8b1 100644
--- a/include/asm-x86_64/pgalloc.h
+++ b/include/asm-x86_64/pgalloc.h
@@ -45,12 +45,39 @@ static inline void pud_free (pud_t *pud)
         free_page((unsigned long)pud);
 }
 
+static inline void pgd_list_add(pgd_t *pgd)
+{
+        struct page *page = virt_to_page(pgd);
+
+        spin_lock(&pgd_lock);
+        page->index = (pgoff_t)pgd_list;
+        if (pgd_list)
+                pgd_list->private = (unsigned long)&page->index;
+        pgd_list = page;
+        page->private = (unsigned long)&pgd_list;
+        spin_unlock(&pgd_lock);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+        struct page *next, **pprev, *page = virt_to_page(pgd);
+
+        spin_lock(&pgd_lock);
+        next = (struct page *)page->index;
+        pprev = (struct page **)page->private;
+        *pprev = next;
+        if (next)
+                next->private = (unsigned long)pprev;
+        spin_unlock(&pgd_lock);
+}
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
         unsigned boundary;
         pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
         if (!pgd)
                 return NULL;
+        pgd_list_add(pgd);
         /*
          * Copy kernel pointers in from init.
          * Could keep a freelist or slab cache of those because the kernel
@@ -67,6 +94,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 static inline void pgd_free(pgd_t *pgd)
 {
         BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+        pgd_list_del(pgd);
         free_page((unsigned long)pgd);
 }
 
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index 715fd94cf577..31e83c3bd022 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -273,7 +273,7 @@ static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)          { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)          { return pte_val(pte) & _PAGE_RW; }
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_huge(pte_t pte)           { return (pte_val(pte) & __LARGE_PTE) == __LARGE_PTE; }
+static inline int pte_huge(pte_t pte)           { return pte_val(pte) & _PAGE_PSE; }
 
 static inline pte_t pte_rdprotect(pte_t pte)    { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
 static inline pte_t pte_exprotect(pte_t pte)    { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
@@ -285,7 +285,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _
 static inline pte_t pte_mkdirty(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)      { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
-static inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | __LARGE_PTE)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)       { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
 
 struct vm_area_struct;
 
@@ -293,19 +293,19 @@ static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned
 {
         if (!pte_dirty(*ptep))
                 return 0;
-        return test_and_clear_bit(_PAGE_BIT_DIRTY, ptep);
+        return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte);
 }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
         if (!pte_young(*ptep))
                 return 0;
-        return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep);
+        return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
 }
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        clear_bit(_PAGE_BIT_RW, ptep);
+        clear_bit(_PAGE_BIT_RW, &ptep->pte);
 }
 
 /*
@@ -420,6 +420,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)           ((pte_t) { (x).val })
 
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+void vmalloc_sync_all(void);
+
 #endif /* !__ASSEMBLY__ */
 
 extern int kern_addr_valid(unsigned long addr); 
diff --git a/include/asm-x86_64/poll.h b/include/asm-x86_64/poll.h
index c43cbba31913..c0475a9d8bb8 100644
--- a/include/asm-x86_64/poll.h
+++ b/include/asm-x86_64/poll.h
@@ -16,6 +16,7 @@
 #define POLLWRBAND      0x0200
 #define POLLMSG         0x0400
 #define POLLREMOVE      0x1000
+#define POLLRDHUP       0x2000
 
 struct pollfd {
         int fd;
diff --git a/include/asm-x86_64/processor.h b/include/asm-x86_64/processor.h
index 8c8d88c036ed..37a3ec433ee5 100644
--- a/include/asm-x86_64/processor.h
+++ b/include/asm-x86_64/processor.h
@@ -20,6 +20,7 @@
 #include <asm/mmsegment.h>
 #include <asm/percpu.h>
 #include <linux/personality.h>
+#include <linux/cpumask.h>
 
 #define TF_MASK         0x00000100
 #define IF_MASK         0x00000200
@@ -65,6 +66,9 @@ struct cpuinfo_x86 {
         __u32   x86_power;      
         __u32   extended_cpuid_level;   /* Max extended CPUID function supported */
         unsigned long loops_per_jiffy;
+#ifdef CONFIG_SMP
+        cpumask_t llc_shared_map;       /* cpus sharing the last level cache */
+#endif
         __u8    apicid;
         __u8    booted_cores;   /* number of cores as seen by OS */
 } ____cacheline_aligned;
@@ -354,9 +358,6 @@ struct extended_sigtable {
         struct extended_signature sigs[0];
 };
 
-/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */
-#define MICROCODE_IOCFREE       _IO('6',0)
-
 
 #define ASM_NOP1 K8_NOP1
 #define ASM_NOP2 K8_NOP2
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index 3ba8fd45fcb3..8abf2a43c944 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -53,8 +53,6 @@ extern int sysctl_vsyscall;
 extern int nohpet;
 extern unsigned long vxtime_hz;
 
-extern void do_softirq_thunk(void);
-
 extern int numa_setup(char *opt);
 
 extern int setup_early_printk(char *); 
@@ -129,7 +127,6 @@ extern int fix_aperture;
 #define iommu_aperture 0
 #define iommu_aperture_allowed 0
 #endif
-extern int force_iommu;
 
 extern int reboot_force;
 extern int notsc_setup(char *);
diff --git a/include/asm-x86_64/smp.h b/include/asm-x86_64/smp.h
index 9ccbb2cfd5c0..a4fdaeb5c397 100644
--- a/include/asm-x86_64/smp.h
+++ b/include/asm-x86_64/smp.h
@@ -56,6 +56,7 @@ extern cpumask_t cpu_sibling_map[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 extern u8 phys_proc_id[NR_CPUS];
 extern u8 cpu_core_id[NR_CPUS];
+extern u8 cpu_llc_id[NR_CPUS];
 
 #define SMP_TRAMPOLINE_BASE 0x6000
 
diff --git a/include/asm-x86_64/string.h b/include/asm-x86_64/string.h
index a3493ee282bb..ee6bf275349e 100644
--- a/include/asm-x86_64/string.h
+++ b/include/asm-x86_64/string.h
@@ -40,26 +40,15 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 
 
 #define __HAVE_ARCH_MEMSET
-#define memset __builtin_memset
+void *memset(void *s, int c, size_t n);
 
 #define __HAVE_ARCH_MEMMOVE
 void * memmove(void * dest,const void *src,size_t count);
 
-/* Use C out of line version for memcmp */ 
-#define memcmp __builtin_memcmp
 int memcmp(const void * cs,const void * ct,size_t count);
-
-/* out of line string functions use always C versions */ 
-#define strlen __builtin_strlen
 size_t strlen(const char * s);
-
-#define strcpy __builtin_strcpy
-char * strcpy(char * dest,const char *src);
-
-#define strcat __builtin_strcat
-char * strcat(char * dest, const char * src);
-
-#define strcmp __builtin_strcmp
+char *strcpy(char * dest,const char *src);
+char *strcat(char * dest, const char * src);
 int strcmp(const char * cs,const char * ct);
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86_64/suspend.h b/include/asm-x86_64/suspend.h
index bb9f40597d09..bc7f81715e5e 100644
--- a/include/asm-x86_64/suspend.h
+++ b/include/asm-x86_64/suspend.h
@@ -39,9 +39,7 @@ extern unsigned long saved_context_r12, saved_context_r13, saved_context_r14, sa
 extern unsigned long saved_context_eflags;
 
 #define loaddebug(thread,register) \
-               __asm__("movq %0,%%db" #register  \
-                       : /* no output */ \
-                       :"r" ((thread)->debugreg##register))
+        set_debugreg((thread)->debugreg##register, register)
 
 extern void fix_processor_context(void);
 
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
index b7f66034ae7a..397598980228 100644
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -70,12 +70,6 @@ extern void load_gs_index(unsigned);
                 ".previous"                     \
                 : :"r" (value), "r" (0))
 
-#define set_debug(value,register) \
-                __asm__("movq %0,%%db" #register  \
-                : /* no output */ \
-                :"r" ((unsigned long) value))
-
-
 #ifdef __KERNEL__
 struct alt_instr { 
         __u8 *instr;            /* original instruction */
diff --git a/include/asm-x86_64/topology.h b/include/asm-x86_64/topology.h
index c642f5d9882d..9db54e9d17bb 100644
--- a/include/asm-x86_64/topology.h
+++ b/include/asm-x86_64/topology.h
@@ -68,4 +68,6 @@ extern int __node_distance(int, int);
 
 #include <asm-generic/topology.h>
 
+extern cpumask_t cpu_coregroup_map(int cpu);
+
 #endif
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index da0341c57949..f21ff2c1e960 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -605,8 +605,14 @@ __SYSCALL(__NR_pselect6, sys_ni_syscall)	/* for now */
 __SYSCALL(__NR_ppoll,   sys_ni_syscall)         /* for now */
 #define __NR_unshare            272
 __SYSCALL(__NR_unshare, sys_unshare)
-
-#define __NR_syscall_max __NR_unshare
+#define __NR_set_robust_list    273
+__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
+#define __NR_get_robust_list    274
+__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
+#define __NR_splice             275
+__SYSCALL(__NR_splice, sys_splice)
+
+#define __NR_syscall_max __NR_splice
 
 #ifndef __NO_STUBS