280 files changed, 4799 insertions, 4931 deletions

diff --git a/.gitignore b/.gitignore
index 27c3e839b54e..22fb8fa9bc3d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -26,6 +26,7 @@ vmlinux*
 !vmlinux.lds.S
 System.map
 Module.symvers
+!.gitignore
 
 #
 # Generated include files
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 4a37e25e694c..e5c1df52a876 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -347,7 +347,35 @@ connects the CPUs in a SMP system. This means that an error has been detected,
 the IO-APIC automatically retry the transmission, so it should not be a big
 problem, but you should read the SMP-FAQ.
 
-In this context it could be interesting to note the new irq directory in 2.4.
+In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
+/proc/interrupts to display every IRQ vector in use by the system, not
+just those considered 'most important'.  The new vectors are:
+
+  THR -- interrupt raised when a machine check threshold counter
+  (typically counting ECC corrected errors of memory or cache) exceeds
+  a configurable threshold.  Only available on some systems.
+
+  TRM -- a thermal event interrupt occurs when a temperature threshold
+  has been exceeded for the CPU.  This interrupt may also be generated
+  when the temperature drops back to normal.
+
+  SPU -- a spurious interrupt is some interrupt that was raised then lowered
+  by some IO device before it could be fully processed by the APIC.  Hence
+  the APIC sees the interrupt but does not know what device it came from.
+  For this case the APIC will generate the interrupt with a IRQ vector
+  of 0xff. This might also be generated by chipset bugs.
+
+  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
+  sent from one CPU to another per the needs of the OS.  Typically,
+  their statistics are used by kernel developers and interested users to
+  determine the occurance of interrupt of the given type.
+
+The above IRQ vectors are displayed only when relevent.  For example,
+the threshold vector does not exist on x86_64 platforms.  Others are
+suppressed when the system is a uniprocessor.  As of this writing, only
+i386 and x86_64 platforms support the new IRQ vector displays.
+
+Of some interest is the introduction of the /proc/irq directory to 2.4.
 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
 irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 63bda3637085..98cf90f2631d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -994,6 +994,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         mce             [X86-32] Machine Check Exception
 
+        mce=option      [X86-64] See Documentation/x86_64/boot-options.txt
+
         md=             [HW] RAID subsystems devices and level
                         See Documentation/md.txt.
 
diff --git a/Makefile b/Makefile
index ed65de7078c7..529b9048d97e 100644
--- a/Makefile
+++ b/Makefile
@@ -1325,8 +1325,8 @@ ALLSOURCE_ARCHS := $(ARCH) $(SRCARCH)
 endif
 
 define find-sources
-        ( for ARCH in $(ALLSOURCE_ARCHS) ; do \
-               find $(__srctree)arch/$${SRCARCH} $(RCS_FIND_IGNORE) \
+        ( for arch in $(ALLSOURCE_ARCHS) ; do \
+               find $(__srctree)arch/$${arch} $(RCS_FIND_IGNORE) \
                     -name $1 -print; \
           done ; \
           find $(__srctree)security/selinux/include $(RCS_FIND_IGNORE) \
@@ -1334,8 +1334,8 @@ define find-sources
           find $(__srctree)include $(RCS_FIND_IGNORE) \
                \( -name config -o -name 'asm-*' \) -prune \
                -o -name $1 -print; \
-          for ARCH in $(ALLINCLUDE_ARCHS) ; do \
-               find $(__srctree)include/asm-$${SRCARCH} $(RCS_FIND_IGNORE) \
+          for arch in $(ALLINCLUDE_ARCHS) ; do \
+               find $(__srctree)include/asm-$${arch} $(RCS_FIND_IGNORE) \
                     -name $1 -print; \
           done ; \
           find $(__srctree)include/asm-generic $(RCS_FIND_IGNORE) \
diff --git a/arch/i386/.gitignore b/arch/i386/.gitignore
new file mode 100644
index 000000000000..36ef4c374d25
--- /dev/null
+++ b/arch/i386/.gitignore
@@ -0,0 +1 @@
+boot
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 7a95c58947e4..b84d5050e92e 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -146,6 +146,7 @@ config X86_ELAN
 
 config X86_VOYAGER
         bool "Voyager (NCR)"
+        select SMP if !BROKEN
         help
           Voyager is an MCA-based 32-way capable SMP architecture proprietary
           to NCR Corp.  Machine classes 345x/35xx/4100/51xx are Voyager-based.
diff --git a/arch/i386/Kconfig.cpu b/arch/i386/Kconfig.cpu
index 11a24d54f27b..0e2adadf5905 100644
--- a/arch/i386/Kconfig.cpu
+++ b/arch/i386/Kconfig.cpu
@@ -109,16 +109,42 @@ config MCORE2
         help
           Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx)
           CPUs. You can distinguish newer from older Xeons by the CPU family
-          in /proc/cpuinfo. Newer ones have 6.
+          in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo)
 
 config MPENTIUM4
         bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
         help
           Select this for Intel Pentium 4 chips.  This includes the
-          Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M
-          (not Pentium M) chips.  This option enables compile flags
-          optimized for the chip, uses the correct cache shift, and
-          applies any applicable Pentium III optimizations.
+          Pentium 4, Pentium D, P4-based Celeron and Xeon, and
+          Pentium-4 M (not Pentium M) chips.  This option enables compile
+          flags optimized for the chip, uses the correct cache line size, and
+          applies any applicable optimizations.
+
+          CPUIDs: F[0-6][1-A] (in /proc/cpuinfo show = cpu family : 15 )
+
+          Select this for:
+            Pentiums (Pentium 4, Pentium D, Celeron, Celeron D) corename:
+                -Willamette
+                -Northwood
+                -Mobile Pentium 4
+                -Mobile Pentium 4 M
+                -Extreme Edition (Gallatin)
+                -Prescott
+                -Prescott 2M
+                -Cedar Mill
+                -Presler
+                -Smithfiled
+            Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
+                -Foster
+                -Prestonia
+                -Gallatin
+                -Nocona
+                -Irwindale
+                -Cranford
+                -Potomac
+                -Paxville
+                -Dempsey
+
 
 config MK6
         bool "K6/K6-II/K6-III"
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index cdae36435e21..e2edda255a84 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -18,18 +18,35 @@ $(obj)/syscall32_syscall.o: \
         $(foreach F,sysenter syscall,$(obj)/vsyscall-$F.so)
 
 # Teach kbuild about targets
-targets := $(foreach F,sysenter syscall,vsyscall-$F.o vsyscall-$F.so)
+targets := $(foreach F,$(addprefix vsyscall-,sysenter syscall),\
+                     $F.o $F.so $F.so.dbg)
 
 # The DSO images are built using a special linker script
 quiet_cmd_syscall = SYSCALL $@
-      cmd_syscall = $(CC) -m32 -nostdlib -shared -s \
+      cmd_syscall = $(CC) -m32 -nostdlib -shared \
                           $(call ld-option, -Wl$(comma)--hash-style=sysv) \
                            -Wl,-soname=linux-gate.so.1 -o $@ \
                            -Wl,-T,$(filter-out FORCE,$^)
 
-$(obj)/vsyscall-sysenter.so $(obj)/vsyscall-syscall.so: \
-$(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+        $(call if_changed,objcopy)
+
+$(obj)/vsyscall-sysenter.so.dbg $(obj)/vsyscall-syscall.so.dbg: \
+$(obj)/vsyscall-%.so.dbg: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
         $(call if_changed,syscall)
 
 AFLAGS_vsyscall-sysenter.o = -m32 -Wa,-32
 AFLAGS_vsyscall-syscall.o = -m32 -Wa,-32
+
+vdsos := vdso32-sysenter.so vdso32-syscall.so
+
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(@:vdso32-%.so=$(obj)/vsyscall-%.so.dbg) \
+                            $(MODLIB)/vdso/$@
+
+$(vdsos):
+        @mkdir -p $(MODLIB)/vdso
+        $(call cmd,vdso_install)
+
+vdso_install: $(vdsos)
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 7cf1c29bf90e..f82e1a94fcb7 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -420,6 +420,8 @@ beyond_if:
         (regs)->eflags = 0x200;
         (regs)->cs = __USER32_CS;
         (regs)->ss = __USER32_DS;
+        regs->r8 = regs->r9 = regs->r10 = regs->r11 =
+        regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
         set_fs(USER_DS);
         if (unlikely(current->ptrace & PT_PTRACED)) {
                 if (current->ptrace & PT_TRACE_EXEC)
diff --git a/arch/x86/ia32/ia32_binfmt.c b/arch/x86/ia32/ia32_binfmt.c
index d3c53e8b05c0..118b9f9ff499 100644
--- a/arch/x86/ia32/ia32_binfmt.c
+++ b/arch/x86/ia32/ia32_binfmt.c
@@ -112,11 +112,8 @@ struct elf_prpsinfo
         char    pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */
 };
 
-#define __STR(x) #x
-#define STR(x) __STR(x)
-
 #define _GET_SEG(x) \
-        ({ __u32 seg; asm("movl %%" STR(x) ",%0" : "=r"(seg)); seg; })
+        ({ __u32 seg; asm("movl %%" __stringify(x) ",%0" : "=r"(seg)); seg; })
 
 /* Assumes current==process to be dumped */
 #define ELF_CORE_COPY_REGS(pr_reg, regs)                \
diff --git a/arch/x86/ia32/ptrace32.c b/arch/x86/ia32/ptrace32.c
index 4a233ad6269c..f52770ef0ee3 100644
--- a/arch/x86/ia32/ptrace32.c
+++ b/arch/x86/ia32/ptrace32.c
@@ -228,6 +228,8 @@ static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data)
         return ret;
 }
 
+#define COMPAT_GDT_ENTRY_TLS_MIN 6
+
 asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 {
         struct task_struct *child;
@@ -246,8 +248,6 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
         case PTRACE_SYSCALL:
         case PTRACE_OLDSETOPTIONS:
         case PTRACE_SETOPTIONS:
-        case PTRACE_SET_THREAD_AREA:
-        case PTRACE_GET_THREAD_AREA:
                 return sys_ptrace(request, pid, addr, data); 
 
         default:
@@ -271,6 +271,12 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
         case PTRACE_SETSIGINFO:
         case PTRACE_GETSIGINFO:
                 return ptrace32_siginfo(request, pid, addr, data);
+
+        case PTRACE_SET_THREAD_AREA:
+        case PTRACE_GET_THREAD_AREA:
+                return sys_ptrace(request, pid,
+                        addr + GDT_ENTRY_TLS_MIN - COMPAT_GDT_ENTRY_TLS_MIN,
+                        data);
         }
 
         child = ptrace_get_task_struct(pid);
diff --git a/arch/x86/kernel/.gitignore b/arch/x86/kernel/.gitignore
index 40836ad9079c..4ea38a39aed4 100644
--- a/arch/x86/kernel/.gitignore
+++ b/arch/x86/kernel/.gitignore
@@ -1 +1,2 @@
 vsyscall.lds
+vsyscall_32.lds
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 45855c97923e..38573340b143 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -3,3 +3,7 @@ include ${srctree}/arch/x86/kernel/Makefile_32
 else
 include ${srctree}/arch/x86/kernel/Makefile_64
 endif
+
+# Workaround to delete .lds files with make clean
+# The problem is that we do not enter Makefile_32 with make clean.
+clean-files := vsyscall*.lds vsyscall*.so
diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32
index 7ff02063b858..a3fa11f8f460 100644
--- a/arch/x86/kernel/Makefile_32
+++ b/arch/x86/kernel/Makefile_32
@@ -51,7 +51,7 @@ obj-$(CONFIG_SCx200)		+= scx200_32.o
 # We must build both images before we can assemble it.
 # Note: kbuild does not track this dependency due to usage of .incbin
 $(obj)/vsyscall_32.o: $(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so
-targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so)
+targets += $(foreach F,int80 sysenter,vsyscall-$F_32.o vsyscall-$F_32.so)
 targets += vsyscall-note_32.o vsyscall_32.lds
 
 # The DSO images are built using a special linker script.
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 11b03d3c6fda..3bd2688bd443 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -63,11 +63,11 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
 /* Use inline assembly to define this because the nops are defined
    as inline assembly strings in the include files and we cannot
    get them easily into strings. */
-asm("\t.data\nintelnops: "
+asm("\t.section .rodata, \"a\"\nintelnops: "
         GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
         GENERIC_NOP7 GENERIC_NOP8);
-extern unsigned char intelnops[];
-static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char intelnops[];
+static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
         NULL,
         intelnops,
         intelnops + 1,
@@ -81,11 +81,11 @@ static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
 #endif
 
 #ifdef K8_NOP1
-asm("\t.data\nk8nops: "
+asm("\t.section .rodata, \"a\"\nk8nops: "
         K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
         K8_NOP7 K8_NOP8);
-extern unsigned char k8nops[];
-static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k8nops[];
+static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
         NULL,
         k8nops,
         k8nops + 1,
@@ -99,11 +99,11 @@ static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
 #endif
 
 #ifdef K7_NOP1
-asm("\t.data\nk7nops: "
+asm("\t.section .rodata, \"a\"\nk7nops: "
         K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
         K7_NOP7 K7_NOP8);
-extern unsigned char k7nops[];
-static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k7nops[];
+static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
         NULL,
         k7nops,
         k7nops + 1,
@@ -116,28 +116,49 @@ static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
 };
 #endif
 
+#ifdef P6_NOP1
+asm("\t.section .rodata, \"a\"\np6nops: "
+        P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
+        P6_NOP7 P6_NOP8);
+extern const unsigned char p6nops[];
+static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
+        NULL,
+        p6nops,
+        p6nops + 1,
+        p6nops + 1 + 2,
+        p6nops + 1 + 2 + 3,
+        p6nops + 1 + 2 + 3 + 4,
+        p6nops + 1 + 2 + 3 + 4 + 5,
+        p6nops + 1 + 2 + 3 + 4 + 5 + 6,
+        p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
-static inline unsigned char** find_nop_table(void)
+static inline const unsigned char*const * find_nop_table(void)
 {
-        return k8_nops;
+        return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+               boot_cpu_data.x86 < 6 ? k8_nops : p6_nops;
 }
 
 #else /* CONFIG_X86_64 */
 
-static struct nop {
+static const struct nop {
         int cpuid;
-        unsigned char **noptable;
+        const unsigned char *const *noptable;
 } noptypes[] = {
         { X86_FEATURE_K8, k8_nops },
         { X86_FEATURE_K7, k7_nops },
+        { X86_FEATURE_P4, p6_nops },
+        { X86_FEATURE_P3, p6_nops },
         { -1, NULL }
 };
 
-static unsigned char** find_nop_table(void)
+static const unsigned char*const * find_nop_table(void)
 {
-        unsigned char **noptable = intel_nops;
+        const unsigned char *const *noptable = intel_nops;
         int i;
 
         for (i = 0; noptypes[i].cpuid >= 0; i++) {
@@ -154,7 +175,7 @@ static unsigned char** find_nop_table(void)
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void add_nops(void *insns, unsigned int len)
 {
-        unsigned char **noptable = find_nop_table();
+        const unsigned char *const *noptable = find_nop_table();
 
         while (len > 0) {
                 unsigned int noplen = len;
@@ -369,8 +390,8 @@ void apply_paravirt(struct paravirt_patch_site *start,
                 BUG_ON(p->len > MAX_PATCH_LEN);
                 /* prep the buffer with the original instructions */
                 memcpy(insnbuf, p->instr, p->len);
-                used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf,
-                                          (unsigned long)p->instr, p->len);
+                used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf,
+                                         (unsigned long)p->instr, p->len);
 
                 BUG_ON(used > p->len);
 
@@ -415,9 +436,6 @@ void __init alternative_instructions(void)
                         alternatives_smp_unlock(__smp_locks, __smp_locks_end,
                                                 _text, _etext);
                 }
-                free_init_pages("SMP alternatives",
-                                (unsigned long)__smp_locks,
-                                (unsigned long)__smp_locks_end);
         } else {
                 alternatives_smp_module_add(NULL, "core kernel",
                                             __smp_locks, __smp_locks_end,
@@ -428,6 +446,11 @@ void __init alternative_instructions(void)
         apply_paravirt(__parainstructions, __parainstructions_end);
         local_irq_restore(flags);
 
+        if (smp_alt_once)
+                free_init_pages("SMP alternatives",
+                                (unsigned long)__smp_locks,
+                                (unsigned long)__smp_locks_end);
+
         restart_nmi();
 #ifdef CONFIG_X86_MCE
         restart_mce();
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 3d67ae18d762..793341fffc81 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1277,6 +1277,7 @@ void smp_spurious_interrupt(struct pt_regs *regs)
         /* see sw-dev-man vol 3, chapter 7.4.13.5 */
         printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
                "should never happen.\n", smp_processor_id());
+        __get_cpu_var(irq_stat).irq_spurious_count++;
         irq_exit();
 }
 
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 09b82093bc75..f47bc493dba9 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -974,15 +974,12 @@ void __init setup_boot_APIC_clock (void)
  */
 void __cpuinit check_boot_apic_timer_broadcast(void)
 {
-        struct clock_event_device *levt = &per_cpu(lapic_events, boot_cpu_id);
-
         if (!disable_apic_timer ||
             (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
                 return;
 
         printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
         lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-        levt->features |= CLOCK_EVT_FEAT_DUMMY;
 
         local_irq_enable();
         clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
@@ -1143,6 +1140,7 @@ asmlinkage void smp_spurious_interrupt(void)
         if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
                 ack_APIC_irq();
 
+        add_pda(irq_spurious_count, 1);
         irq_exit();
 }
 
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 8029742c0fc1..f1b7cdda82b3 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -116,12 +116,14 @@ void foo(void)
 
 #ifdef CONFIG_PARAVIRT
         BLANK();
-        OFFSET(PARAVIRT_enabled, paravirt_ops, paravirt_enabled);
-        OFFSET(PARAVIRT_irq_disable, paravirt_ops, irq_disable);
-        OFFSET(PARAVIRT_irq_enable, paravirt_ops, irq_enable);
-        OFFSET(PARAVIRT_irq_enable_sysexit, paravirt_ops, irq_enable_sysexit);
-        OFFSET(PARAVIRT_iret, paravirt_ops, iret);
-        OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
+        OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
+        OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
+        OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
+        OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
+        OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
+        OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+        OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+        OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 #endif
 
 #ifdef CONFIG_XEN
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index dcf6bbb1c7c0..5f8af875f457 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -4,6 +4,7 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#include <asm/mach_apic.h>
 
 #include "cpu.h"
 
@@ -45,13 +46,17 @@ static __cpuinit int amd_apic_timer_broken(void)
         case CPUID_XFAM_10H:
         case CPUID_XFAM_11H:
                 rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-                if (lo & ENABLE_C1E_MASK)
+                if (lo & ENABLE_C1E_MASK) {
+                        if (smp_processor_id() != boot_cpu_physical_apicid)
+                                printk(KERN_INFO "AMD C1E detected late. "
+                                       "        Force timer broadcast.\n");
                         return 1;
-                break;
-        default:
-                /* err on the side of caution */
+                }
+                break;
+        default:
+                /* err on the side of caution */
                 return 1;
-        }
+        }
         return 0;
 }
 #endif
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index 7decd6a50ffa..f3686a5f2308 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -565,7 +565,7 @@ static unsigned int powernow_get(unsigned int cpu)
 }
 
 
-static int __init acer_cpufreq_pst(struct dmi_system_id *d)
+static int __init acer_cpufreq_pst(const struct dmi_system_id *d)
 {
         printk(KERN_WARNING "%s laptop with broken PST tables in BIOS detected.\n", d->ident);
         printk(KERN_WARNING "You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n");
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dc4e08147b1f..cc8c501b9f39 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/processor.h>
+#include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/uaccess.h>
 
@@ -19,8 +20,6 @@
 #include <mach_apic.h>
 #endif
 
-extern int trap_init_f00f_bug(void);
-
 #ifdef CONFIG_X86_INTEL_USERCOPY
 /*
  * Alignment at which movsl is preferred for bulk memory copies.
@@ -95,6 +94,20 @@ static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
                 return 1;
 }
 
+#ifdef CONFIG_X86_F00F_BUG
+static void __cpuinit trap_init_f00f_bug(void)
+{
+        __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
+
+        /*
+         * Update the IDT descriptor and reload the IDT so that
+         * it uses the read-only mapped virtual address.
+         */
+        idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+        load_idt(&idt_descr);
+}
+#endif
+
 static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
         unsigned int l2 = 0;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index db6c25aa5776..1826395ebeeb 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -170,15 +170,15 @@ union l3_cache {
         unsigned val;
 };
 
-static const unsigned short assocs[] = {
+static unsigned short assocs[] __cpuinitdata = {
         [1] = 1, [2] = 2, [4] = 4, [6] = 8,
         [8] = 16, [0xa] = 32, [0xb] = 48,
         [0xc] = 64,
         [0xf] = 0xffff // ??
 };
 
-static const unsigned char levels[] = { 1, 1, 2, 3 };
-static const unsigned char types[] = { 1, 2, 3, 3 };
+static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
+static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
 
 static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
                        union _cpuid4_leaf_ebx *ebx,
@@ -493,8 +493,8 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
         }
 }
 #else
-static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
-static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
+static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
 #endif
 
 static void free_cache_attributes(unsigned int cpu)
@@ -794,8 +794,9 @@ static int __cpuinit cache_sysfs_init(void)
         register_hotcpu_notifier(&cacheinfo_cpu_notifier);
 
         for_each_online_cpu(i) {
-                cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE,
-                        (void *)(long)i);
+                struct sys_device *sys_dev = get_cpu_sysdev((unsigned int)i);
+
+                cache_add_dev(sys_dev);
         }
 
         return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index 1509edfb2313..be4dabfee1f5 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -61,6 +61,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs)
 {
         irq_enter();
         vendor_thermal_interrupt(regs);
+        __get_cpu_var(irq_stat).irq_thermal_count++;
         irq_exit();
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 1203dc5ab87a..494d320d909b 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -152,7 +152,7 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
         return NOTIFY_OK;
 }
 
-static struct notifier_block thermal_throttle_cpu_notifier =
+static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
 {
         .notifier_call = thermal_throttle_cpu_callback,
 };
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index c48b6fea5ab4..5e4be30ff903 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -738,13 +738,7 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-        int cpu = get_cpu();
-
-        if (cpu == 0)
-                mtrr_save_fixed_ranges(NULL);
-        else
-                smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
-        put_cpu();
+        smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
 }
 
 static int __init mtrr_init_finialize(void)
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 93fecd4b03de..54cdbf1a40f1 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -34,7 +34,7 @@ struct wd_ops {
         u64 checkbit;
 };
 
-static struct wd_ops *wd_ops;
+static const struct wd_ops *wd_ops;
 
 /* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
  * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
@@ -317,7 +317,7 @@ static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
         write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
 }
 
-static struct wd_ops k7_wd_ops = {
+static const struct wd_ops k7_wd_ops = {
         .reserve = single_msr_reserve,
         .unreserve = single_msr_unreserve,
         .setup = setup_k7_watchdog,
@@ -380,7 +380,7 @@ static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
         write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz);
 }
 
-static struct wd_ops p6_wd_ops = {
+static const struct wd_ops p6_wd_ops = {
         .reserve = single_msr_reserve,
         .unreserve = single_msr_unreserve,
         .setup = setup_p6_watchdog,
@@ -532,7 +532,7 @@ static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
         write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
 }
 
-static struct wd_ops p4_wd_ops = {
+static const struct wd_ops p4_wd_ops = {
         .reserve = p4_reserve,
         .unreserve = p4_unreserve,
         .setup = setup_p4_watchdog,
@@ -550,6 +550,8 @@ static struct wd_ops p4_wd_ops = {
 #define ARCH_PERFMON_NMI_EVENT_SEL      ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
 #define ARCH_PERFMON_NMI_EVENT_UMASK    ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
 
+static struct wd_ops intel_arch_wd_ops;
+
 static int setup_intel_arch_watchdog(unsigned nmi_hz)
 {
         unsigned int ebx;
@@ -591,11 +593,11 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
         wd->perfctr_msr = perfctr_msr;
         wd->evntsel_msr = evntsel_msr;
         wd->cccr_msr = 0;  //unused
-        wd_ops->checkbit = 1ULL << (eax.split.bit_width - 1);
+        intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
         return 1;
 }
 
-static struct wd_ops intel_arch_wd_ops = {
+static struct wd_ops intel_arch_wd_ops __read_mostly = {
         .reserve = single_msr_reserve,
         .unreserve = single_msr_unreserve,
         .setup = setup_intel_arch_watchdog,
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index f4548c93ccf5..70dcf912d9fb 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -43,8 +43,6 @@
 
 static struct class *cpuid_class;
 
-#ifdef CONFIG_SMP
-
 struct cpuid_command {
         u32 reg;
         u32 *data;
@@ -62,25 +60,11 @@ static inline void do_cpuid(int cpu, u32 reg, u32 * data)
 {
         struct cpuid_command cmd;
 
-        preempt_disable();
-        if (cpu == smp_processor_id()) {
-                cpuid(reg, &data[0], &data[1], &data[2], &data[3]);
-        } else {
-                cmd.reg = reg;
-                cmd.data = data;
+        cmd.reg = reg;
+        cmd.data = data;
 
-                smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
-        }
-        preempt_enable();
+        smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
 }
-#else                           /* ! CONFIG_SMP */
-
-static inline void do_cpuid(int cpu, u32 reg, u32 * data)
-{
-        cpuid(reg, &data[0], &data[1], &data[2], &data[3]);
-}
-
-#endif                          /* ! CONFIG_SMP */
 
 static loff_t cpuid_seek(struct file *file, loff_t offset, int orig)
 {
@@ -150,7 +134,7 @@ static const struct file_operations cpuid_fops = {
         .open = cpuid_open,
 };
 
-static int cpuid_device_create(int i)
+static int __cpuinit cpuid_device_create(int i)
 {
         int err = 0;
         struct device *dev;
@@ -161,7 +145,9 @@ static int cpuid_device_create(int i)
         return err;
 }
 
-static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb,
+                                              unsigned long action,
+                                              void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8099fea0a72f..dc7f938e5015 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -437,7 +437,7 @@ ldt_ss:
          * is still available to implement the setting of the high
          * 16-bits in the INTERRUPT_RETURN paravirt-op.
          */
-        cmpl $0, paravirt_ops+PARAVIRT_enabled
+        cmpl $0, pv_info+PARAVIRT_enabled
         jne restore_nocheck
 #endif
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index f1cacd4897f7..3a058bb16409 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -988,7 +988,7 @@ child_rip:
         movq %rsi, %rdi
         call *%rax
         # exit
-        xorl %edi, %edi
+        mov %eax, %edi
         call do_exit
         CFI_ENDPROC
 ENDPROC(child_rip)
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 47496a40e84f..4ae03e3e8294 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -29,8 +29,6 @@ u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly
                                         = { [0 ... NR_CPUS-1] = BAD_APICID };
 EXPORT_SYMBOL(x86_cpu_to_apicid);
 
-u8 x86_cpu_to_log_apicid[NR_CPUS]       = { [0 ... NR_CPUS-1] = BAD_APICID };
-
 struct genapic __read_mostly *genapic = &apic_flat;
 
 /*
diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index ecb01eefdd27..91c7526768ee 100644
--- a/arch/x86/kernel/genapic_flat_64.c
+++ b/arch/x86/kernel/genapic_flat_64.c
@@ -52,7 +52,6 @@ static void flat_init_apic_ldr(void)
 
         num = smp_processor_id();
         id = 1UL << num;
-        x86_cpu_to_log_apicid[num] = id;
         apic_write(APIC_DFR, APIC_DFR_FLAT);
         val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
         val |= SET_APIC_LOGICAL_ID(id);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 9150ca9b5f80..39677965e161 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -51,6 +51,15 @@
  */
 LOW_PAGES = 1<<(32-PAGE_SHIFT_asm)
 
+/*
+ * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate
+ * pagetables from above the 16MB DMA limit, so we'll have to set
+ * up pagetables 16MB more (worst-case):
+ */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+LOW_PAGES = LOW_PAGES + 0x1000000
+#endif
+
 #if PTRS_PER_PMD > 1
 PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD
 #else
@@ -443,6 +452,7 @@ early_page_fault:
 early_fault:
         cld
 #ifdef CONFIG_PRINTK
+        pusha
         movl $(__KERNEL_DS),%eax
         movl %eax,%ds
         movl %eax,%es
@@ -534,8 +544,15 @@ int_msg:
         .asciz "Unknown interrupt or fault at EIP %p %p %p\n"
 
 fault_msg:
-        .ascii "Int %d: CR2 %p  err %p  EIP %p  CS %p  flags %p\n"
-        .asciz "Stack: %p %p %p %p %p %p %p %p\n"
+        .ascii                                                          \
+/* fault info: */       "BUG: Int %d: CR2 %p\n"                         \
+/* pusha regs: */       "     EDI %p  ESI %p  EBP %p  ESP %p\n"         \
+                        "     EBX %p  EDX %p  ECX %p  EAX %p\n"         \
+/* fault frame: */      "     err %p  EIP %p   CS %p  flg %p\n"         \
+                                                                        \
+                        "Stack: %p %p %p %p %p %p %p %p\n"              \
+                        "       %p %p %p %p %p %p %p %p\n"              \
+                        "       %p %p %p %p %p %p %p %p\n"
 
 #include "../../x86/xen/xen-head.S"
 
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index e3d4b73bfdb0..edd39ccf139e 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -1,4 +1,5 @@
 #include <linux/module.h>
+#include <asm/semaphore.h>
 #include <asm/checksum.h>
 #include <asm/desc.h>
 
diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c
index 679bb33acbf1..d34a10cc13a7 100644
--- a/arch/x86/kernel/i8259_32.c
+++ b/arch/x86/kernel/i8259_32.c
@@ -349,7 +349,11 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
  * New motherboards sometimes make IRQ 13 be a PCI interrupt,
  * so allow interrupt sharing.
  */
-static struct irqaction fpu_irq = { math_error_irq, 0, CPU_MASK_NONE, "fpu", NULL, NULL };
+static struct irqaction fpu_irq = {
+        .handler = math_error_irq,
+        .mask = CPU_MASK_NONE,
+        .name = "fpu",
+};
 
 void __init init_ISA_irqs (void)
 {
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
index eb72976cc13c..3f27ea0b9816 100644
--- a/arch/x86/kernel/i8259_64.c
+++ b/arch/x86/kernel/i8259_64.c
@@ -395,7 +395,11 @@ device_initcall(i8259A_init_sysfs);
  * IRQ2 is cascade interrupt to second interrupt controller
  */
 
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+        .handler = no_action,
+        .mask = CPU_MASK_NONE,
+        .name = "cascade",
+};
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
         [0 ... IRQ0_VECTOR - 1] = -1,
         [IRQ0_VECTOR] = 0,
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 4ee1e5ee9b57..5f10c7189534 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1296,6 +1296,11 @@ static void __init setup_IO_APIC_irqs(void)
                         continue;
                 }
 
+                if (!first_notcon) {
+                        apic_printk(APIC_VERBOSE, " not connected.\n");
+                        first_notcon = 1;
+                }
+
                 entry.trigger = irq_trigger(idx);
                 entry.polarity = irq_polarity(idx);
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 966fa1062491..1c2c7bf6a9d3 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -875,6 +875,10 @@ static void __init setup_IO_APIC_irqs(void)
                                 apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin);
                         continue;
                 }
+                if (!first_notcon) {
+                        apic_printk(APIC_VERBOSE, " not connected.\n");
+                        first_notcon = 1;
+                }
 
                 irq = pin_2_irq(idx, apic, pin);
                 add_pin_to_irq(irq, apic, pin);
@@ -885,7 +889,7 @@ static void __init setup_IO_APIC_irqs(void)
         }
 
         if (!first_notcon)
-                apic_printk(APIC_VERBOSE," not connected.\n");
+                apic_printk(APIC_VERBOSE, " not connected.\n");
 }
 
 /*
@@ -1845,7 +1849,7 @@ static struct sysdev_class ioapic_sysdev_class = {
 static int __init ioapic_init_sysfs(void)
 {
         struct sys_device * dev;
-        int i, size, error = 0;
+        int i, size, error;
 
         error = sysdev_class_register(&ioapic_sysdev_class);
         if (error)
@@ -1854,12 +1858,11 @@ static int __init ioapic_init_sysfs(void)
         for (i = 0; i < nr_ioapics; i++ ) {
                 size = sizeof(struct sys_device) + nr_ioapic_registers[i]
                         * sizeof(struct IO_APIC_route_entry);
-                mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+                mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
                 if (!mp_ioapic_data[i]) {
                         printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
                         continue;
                 }
-                memset(mp_ioapic_data[i], 0, size);
                 dev = &mp_ioapic_data[i]->dev;
                 dev->id = i;
                 dev->cls = &ioapic_sysdev_class;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index e173b763f148..d3fde94f7345 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -255,9 +255,17 @@ int show_interrupts(struct seq_file *p, void *v)
         }
 
         if (i < NR_IRQS) {
+                unsigned any_count = 0;
+
                 spin_lock_irqsave(&irq_desc[i].lock, flags);
+#ifndef CONFIG_SMP
+                any_count = kstat_irqs(i);
+#else
+                for_each_online_cpu(j)
+                        any_count |= kstat_cpu(j).irqs[i];
+#endif
                 action = irq_desc[i].action;
-                if (!action)
+                if (!action && !any_count)
                         goto skip;
                 seq_printf(p, "%3d: ",i);
 #ifndef CONFIG_SMP
@@ -268,10 +276,12 @@ int show_interrupts(struct seq_file *p, void *v)
 #endif
                 seq_printf(p, " %8s", irq_desc[i].chip->name);
                 seq_printf(p, "-%-8s", irq_desc[i].name);
-                seq_printf(p, "  %s", action->name);
 
-                for (action=action->next; action; action = action->next)
-                        seq_printf(p, ", %s", action->name);
+                if (action) {
+                        seq_printf(p, "  %s", action->name);
+                        while ((action = action->next) != NULL)
+                                seq_printf(p, ", %s", action->name);
+                }
 
                 seq_putc(p, '\n');
 skip:
@@ -280,14 +290,41 @@ skip:
                 seq_printf(p, "NMI: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", nmi_count(j));
-                seq_putc(p, '\n');
+                seq_printf(p, "  Non-maskable interrupts\n");
 #ifdef CONFIG_X86_LOCAL_APIC
                 seq_printf(p, "LOC: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ",
                                 per_cpu(irq_stat,j).apic_timer_irqs);
-                seq_putc(p, '\n');
+                seq_printf(p, "  Local timer interrupts\n");
 #endif
+#ifdef CONFIG_SMP
+                seq_printf(p, "RES: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ",
+                                per_cpu(irq_stat,j).irq_resched_count);
+                seq_printf(p, "  Rescheduling interrupts\n");
+                seq_printf(p, "CAL: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ",
+                                per_cpu(irq_stat,j).irq_call_count);
+                seq_printf(p, "  function call interrupts\n");
+                seq_printf(p, "TLB: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ",
+                                per_cpu(irq_stat,j).irq_tlb_count);
+                seq_printf(p, "  TLB shootdowns\n");
+#endif
+                seq_printf(p, "TRM: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ",
+                                per_cpu(irq_stat,j).irq_thermal_count);
+                seq_printf(p, "  Thermal event interrupts\n");
+                seq_printf(p, "SPU: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ",
+                                per_cpu(irq_stat,j).irq_spurious_count);
+                seq_printf(p, "  Spurious interrupts\n");
                 seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
                 seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 865669efc540..6b5c730d67b9 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -62,9 +62,17 @@ int show_interrupts(struct seq_file *p, void *v)
         }
 
         if (i < NR_IRQS) {
+                unsigned any_count = 0;
+
                 spin_lock_irqsave(&irq_desc[i].lock, flags);
+#ifndef CONFIG_SMP
+                any_count = kstat_irqs(i);
+#else
+                for_each_online_cpu(j)
+                        any_count |= kstat_cpu(j).irqs[i];
+#endif
                 action = irq_desc[i].action;
-                if (!action) 
+                if (!action && !any_count)
                         goto skip;
                 seq_printf(p, "%3d: ",i);
 #ifndef CONFIG_SMP
@@ -76,9 +84,11 @@ int show_interrupts(struct seq_file *p, void *v)
                 seq_printf(p, " %8s", irq_desc[i].chip->name);
                 seq_printf(p, "-%-8s", irq_desc[i].name);
 
-                seq_printf(p, "  %s", action->name);
-                for (action=action->next; action; action = action->next)
-                        seq_printf(p, ", %s", action->name);
+                if (action) {
+                        seq_printf(p, "  %s", action->name);
+                        while ((action = action->next) != NULL)
+                                seq_printf(p, ", %s", action->name);
+                }
                 seq_putc(p, '\n');
 skip:
                 spin_unlock_irqrestore(&irq_desc[i].lock, flags);
@@ -86,11 +96,37 @@ skip:
                 seq_printf(p, "NMI: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
-                seq_putc(p, '\n');
+                seq_printf(p, "  Non-maskable interrupts\n");
                 seq_printf(p, "LOC: ");
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
-                seq_putc(p, '\n');
+                seq_printf(p, "  Local timer interrupts\n");
+#ifdef CONFIG_SMP
+                seq_printf(p, "RES: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_resched_count);
+                seq_printf(p, "  Rescheduling interrupts\n");
+                seq_printf(p, "CAL: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
+                seq_printf(p, "  function call interrupts\n");
+                seq_printf(p, "TLB: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
+                seq_printf(p, "  TLB shootdowns\n");
+#endif
+                seq_printf(p, "TRM: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
+                seq_printf(p, "  Thermal event interrupts\n");
+                seq_printf(p, "THR: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
+                seq_printf(p, "  Threshold APIC interrupts\n");
+                seq_printf(p, "SPU: ");
+                for_each_online_cpu(j)
+                        seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
+                seq_printf(p, "  Spurious interrupts\n");
                 seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
         }
         return 0;
diff --git a/arch/x86/kernel/ldt_32.c b/arch/x86/kernel/ldt_32.c
index a8b18421863a..9ff90a27c45f 100644
--- a/arch/x86/kernel/ldt_32.c
+++ b/arch/x86/kernel/ldt_32.c
@@ -92,13 +92,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
         struct mm_struct * old_mm;
         int retval = 0;
 
-        init_MUTEX(&mm->context.sem);
+        mutex_init(&mm->context.lock);
         mm->context.size = 0;
         old_mm = current->mm;
         if (old_mm && old_mm->context.size > 0) {
-                down(&old_mm->context.sem);
+                mutex_lock(&old_mm->context.lock);
                 retval = copy_ldt(&mm->context, &old_mm->context);
-                up(&old_mm->context.sem);
+                mutex_unlock(&old_mm->context.lock);
         }
         return retval;
 }
@@ -130,7 +130,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
         if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
                 bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
 
-        down(&mm->context.sem);
+        mutex_lock(&mm->context.lock);
         size = mm->context.size*LDT_ENTRY_SIZE;
         if (size > bytecount)
                 size = bytecount;
@@ -138,7 +138,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
         err = 0;
         if (copy_to_user(ptr, mm->context.ldt, size))
                 err = -EFAULT;
-        up(&mm->context.sem);
+        mutex_unlock(&mm->context.lock);
         if (err < 0)
                 goto error_return;
         if (size != bytecount) {
@@ -194,7 +194,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
                         goto out;
         }
 
-        down(&mm->context.sem);
+        mutex_lock(&mm->context.lock);
         if (ldt_info.entry_number >= mm->context.size) {
                 error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1);
                 if (error < 0)
@@ -221,7 +221,7 @@ install:
         error = 0;
 
 out_unlock:
-        up(&mm->context.sem);
+        mutex_unlock(&mm->context.lock);
 out:
         return error;
 }
diff --git a/arch/x86/kernel/ldt_64.c b/arch/x86/kernel/ldt_64.c
index 3796523d616a..60e57abb8e90 100644
--- a/arch/x86/kernel/ldt_64.c
+++ b/arch/x86/kernel/ldt_64.c
@@ -96,13 +96,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
         struct mm_struct * old_mm;
         int retval = 0;
 
-        init_MUTEX(&mm->context.sem);
+        mutex_init(&mm->context.lock);
         mm->context.size = 0;
         old_mm = current->mm;
         if (old_mm && old_mm->context.size > 0) {
-                down(&old_mm->context.sem);
+                mutex_lock(&old_mm->context.lock);
                 retval = copy_ldt(&mm->context, &old_mm->context);
-                up(&old_mm->context.sem);
+                mutex_unlock(&old_mm->context.lock);
         }
         return retval;
 }
@@ -133,7 +133,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
         if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
                 bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
 
-        down(&mm->context.sem);
+        mutex_lock(&mm->context.lock);
         size = mm->context.size*LDT_ENTRY_SIZE;
         if (size > bytecount)
                 size = bytecount;
@@ -141,7 +141,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
         err = 0;
         if (copy_to_user(ptr, mm->context.ldt, size))
                 err = -EFAULT;
-        up(&mm->context.sem);
+        mutex_unlock(&mm->context.lock);
         if (err < 0)
                 goto error_return;
         if (size != bytecount) {
@@ -193,7 +193,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
                         goto out;
         }
 
-        down(&mm->context.sem);
+        mutex_lock(&mm->context.lock);
         if (ldt_info.entry_number >= (unsigned)mm->context.size) {
                 error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1);
                 if (error < 0)
@@ -223,7 +223,7 @@ install:
         error = 0;
 
 out_unlock:
-        up(&mm->context.sem);
+        mutex_unlock(&mm->context.lock);
 out:
         return error;
 }
diff --git a/arch/x86/kernel/mce_64.c b/arch/x86/kernel/mce_64.c
index 97d2b757d6bd..8ca8f8648969 100644
--- a/arch/x86/kernel/mce_64.c
+++ b/arch/x86/kernel/mce_64.c
@@ -695,8 +695,6 @@ static int __init mcheck_disable(char *str)
    mce=nobootlog Don't log MCEs from before booting. */
 static int __init mcheck_enable(char *str)
 {
-        if (*str == '=')
-                str++;
         if (!strcmp(str, "off"))
                 mce_dont_init = 1;
         else if (!strcmp(str, "bootlog") || !strcmp(str,"nobootlog"))
@@ -709,7 +707,7 @@ static int __init mcheck_enable(char *str)
 }
 
 __setup("nomce", mcheck_disable);
-__setup("mce", mcheck_enable);
+__setup("mce=", mcheck_enable);
 
 /* 
  * Sysfs support
diff --git a/arch/x86/kernel/mce_amd_64.c b/arch/x86/kernel/mce_amd_64.c
index 805b62b1e0df..0d2afd96aca4 100644
--- a/arch/x86/kernel/mce_amd_64.c
+++ b/arch/x86/kernel/mce_amd_64.c
@@ -237,6 +237,7 @@ asmlinkage void mce_threshold_interrupt(void)
                 }
         }
 out:
+        add_pda(irq_threshold_count, 1);
         irq_exit();
 }
 
diff --git a/arch/x86/kernel/mce_intel_64.c b/arch/x86/kernel/mce_intel_64.c
index 6551505d8a2c..c17eaf5dd6dd 100644
--- a/arch/x86/kernel/mce_intel_64.c
+++ b/arch/x86/kernel/mce_intel_64.c
@@ -26,6 +26,7 @@ asmlinkage void smp_thermal_interrupt(void)
         if (therm_throt_process(msr_val & 1))
                 mce_log_therm_throt_event(smp_processor_id(), msr_val);
 
+        add_pda(irq_thermal_count, 1);
         irq_exit();
 }
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index c044de310b69..df85c9c13601 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -133,7 +133,7 @@ static const struct file_operations msr_fops = {
         .open = msr_open,
 };
 
-static int msr_device_create(int i)
+static int __cpuinit msr_device_create(int i)
 {
         int err = 0;
         struct device *dev;
@@ -144,7 +144,7 @@ static int msr_device_create(int i)
         return err;
 }
 
-static int msr_class_cpu_callback(struct notifier_block *nfb,
+static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb,
                                 unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
diff --git a/arch/x86/kernel/paravirt_32.c b/arch/x86/kernel/paravirt_32.c
index 739cfb207dd7..6a80d67c2121 100644
--- a/arch/x86/kernel/paravirt_32.c
+++ b/arch/x86/kernel/paravirt_32.c
@@ -42,32 +42,33 @@ void _paravirt_nop(void)
 static void __init default_banner(void)
 {
         printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
-               paravirt_ops.name);
+               pv_info.name);
 }
 
 char *memory_setup(void)
 {
-        return paravirt_ops.memory_setup();
+        return pv_init_ops.memory_setup();
 }
 
 /* Simple instruction patching code. */
-#define DEF_NATIVE(name, code)                                  \
-        extern const char start_##name[], end_##name[];         \
-        asm("start_" #name ": " code "; end_" #name ":")
-
-DEF_NATIVE(irq_disable, "cli");
-DEF_NATIVE(irq_enable, "sti");
-DEF_NATIVE(restore_fl, "push %eax; popf");
-DEF_NATIVE(save_fl, "pushf; pop %eax");
-DEF_NATIVE(iret, "iret");
-DEF_NATIVE(irq_enable_sysexit, "sti; sysexit");
-DEF_NATIVE(read_cr2, "mov %cr2, %eax");
-DEF_NATIVE(write_cr3, "mov %eax, %cr3");
-DEF_NATIVE(read_cr3, "mov %cr3, %eax");
-DEF_NATIVE(clts, "clts");
-DEF_NATIVE(read_tsc, "rdtsc");
-
-DEF_NATIVE(ud2a, "ud2a");
+#define DEF_NATIVE(ops, name, code)                                     \
+        extern const char start_##ops##_##name[], end_##ops##_##name[]; \
+        asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
+
+DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
+DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
+DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
+DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
+DEF_NATIVE(pv_cpu_ops, iret, "iret");
+DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit");
+DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
+DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
+DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
+DEF_NATIVE(pv_cpu_ops, clts, "clts");
+DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
+
+/* Undefined instruction for dealing with missing ops pointers. */
+static const unsigned char ud2a[] = { 0x0f, 0x0b };
 
 static unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
                              unsigned long addr, unsigned len)
@@ -76,37 +77,29 @@ static unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
         unsigned ret;
 
         switch(type) {
-#define SITE(x) case PARAVIRT_PATCH(x): start = start_##x; end = end_##x; goto patch_site
-                SITE(irq_disable);
-                SITE(irq_enable);
-                SITE(restore_fl);
-                SITE(save_fl);
-                SITE(iret);
-                SITE(irq_enable_sysexit);
-                SITE(read_cr2);
-                SITE(read_cr3);
-                SITE(write_cr3);
-                SITE(clts);
-                SITE(read_tsc);
+#define SITE(ops, x)                                            \
+        case PARAVIRT_PATCH(ops.x):                             \
+                start = start_##ops##_##x;                      \
+                end = end_##ops##_##x;                          \
+                goto patch_site
+
+        SITE(pv_irq_ops, irq_disable);
+        SITE(pv_irq_ops, irq_enable);
+        SITE(pv_irq_ops, restore_fl);
+        SITE(pv_irq_ops, save_fl);
+        SITE(pv_cpu_ops, iret);
+        SITE(pv_cpu_ops, irq_enable_sysexit);
+        SITE(pv_mmu_ops, read_cr2);
+        SITE(pv_mmu_ops, read_cr3);
+        SITE(pv_mmu_ops, write_cr3);
+        SITE(pv_cpu_ops, clts);
+        SITE(pv_cpu_ops, read_tsc);
 #undef SITE
 
         patch_site:
                 ret = paravirt_patch_insns(ibuf, len, start, end);
                 break;
 
-        case PARAVIRT_PATCH(make_pgd):
-        case PARAVIRT_PATCH(make_pte):
-        case PARAVIRT_PATCH(pgd_val):
-        case PARAVIRT_PATCH(pte_val):
-#ifdef CONFIG_X86_PAE
-        case PARAVIRT_PATCH(make_pmd):
-        case PARAVIRT_PATCH(pmd_val):
-#endif
-                /* These functions end up returning exactly what
-                   they're passed, in the same registers. */
-                ret = paravirt_patch_nop();
-                break;
-
         default:
                 ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
                 break;
@@ -150,7 +143,7 @@ unsigned paravirt_patch_call(void *insnbuf,
         return 5;
 }
 
-unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
                             unsigned long addr, unsigned len)
 {
         struct branch *b = insnbuf;
@@ -165,22 +158,37 @@ unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
         return 5;
 }
 
+/* Neat trick to map patch type back to the call within the
+ * corresponding structure. */
+static void *get_call_destination(u8 type)
+{
+        struct paravirt_patch_template tmpl = {
+                .pv_init_ops = pv_init_ops,
+                .pv_time_ops = pv_time_ops,
+                .pv_cpu_ops = pv_cpu_ops,
+                .pv_irq_ops = pv_irq_ops,
+                .pv_apic_ops = pv_apic_ops,
+                .pv_mmu_ops = pv_mmu_ops,
+        };
+        return *((void **)&tmpl + type);
+}
+
 unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
                                 unsigned long addr, unsigned len)
 {
-        void *opfunc = *((void **)&paravirt_ops + type);
+        void *opfunc = get_call_destination(type);
         unsigned ret;
 
         if (opfunc == NULL)
                 /* If there's no function, patch it with a ud2a (BUG) */
-                ret = paravirt_patch_insns(insnbuf, len, start_ud2a, end_ud2a);
+                ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a));
         else if (opfunc == paravirt_nop)
                 /* If the operation is a nop, then nop the callsite */
                 ret = paravirt_patch_nop();
-        else if (type == PARAVIRT_PATCH(iret) ||
-                 type == PARAVIRT_PATCH(irq_enable_sysexit))
+        else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+                 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit))
                 /* If operation requires a jmp, then jmp */
-                ret = paravirt_patch_jmp(opfunc, insnbuf, addr, len);
+                ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
         else
                 /* Otherwise call the function; assume target could
                    clobber any caller-save reg */
@@ -205,7 +213,7 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
 
 void init_IRQ(void)
 {
-        paravirt_ops.init_IRQ();
+        pv_irq_ops.init_IRQ();
 }
 
 static void native_flush_tlb(void)
@@ -233,7 +241,7 @@ extern void native_irq_enable_sysexit(void);
 
 static int __init print_banner(void)
 {
-        paravirt_ops.banner();
+        pv_init_ops.banner();
         return 0;
 }
 core_initcall(print_banner);
@@ -273,47 +281,96 @@ int paravirt_disable_iospace(void)
         return ret;
 }
 
-struct paravirt_ops paravirt_ops = {
+static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+
+static inline void enter_lazy(enum paravirt_lazy_mode mode)
+{
+        BUG_ON(x86_read_percpu(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
+        BUG_ON(preemptible());
+
+        x86_write_percpu(paravirt_lazy_mode, mode);
+}
+
+void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+{
+        BUG_ON(x86_read_percpu(paravirt_lazy_mode) != mode);
+        BUG_ON(preemptible());
+
+        x86_write_percpu(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
+}
+
+void paravirt_enter_lazy_mmu(void)
+{
+        enter_lazy(PARAVIRT_LAZY_MMU);
+}
+
+void paravirt_leave_lazy_mmu(void)
+{
+        paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+}
+
+void paravirt_enter_lazy_cpu(void)
+{
+        enter_lazy(PARAVIRT_LAZY_CPU);
+}
+
+void paravirt_leave_lazy_cpu(void)
+{
+        paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+}
+
+enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
+{
+        return x86_read_percpu(paravirt_lazy_mode);
+}
+
+struct pv_info pv_info = {
         .name = "bare hardware",
         .paravirt_enabled = 0,
         .kernel_rpl = 0,
         .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
+};
 
-        .patch = native_patch,
+struct pv_init_ops pv_init_ops = {
+        .patch = native_patch,
         .banner = default_banner,
         .arch_setup = paravirt_nop,
         .memory_setup = machine_specific_memory_setup,
+};
+
+struct pv_time_ops pv_time_ops = {
+        .time_init = hpet_time_init,
         .get_wallclock = native_get_wallclock,
         .set_wallclock = native_set_wallclock,
-        .time_init = hpet_time_init,
+        .sched_clock = native_sched_clock,
+        .get_cpu_khz = native_calculate_cpu_khz,
+};
+
+struct pv_irq_ops pv_irq_ops = {
         .init_IRQ = native_init_IRQ,
+        .save_fl = native_save_fl,
+        .restore_fl = native_restore_fl,
+        .irq_disable = native_irq_disable,
+        .irq_enable = native_irq_enable,
+        .safe_halt = native_safe_halt,
+        .halt = native_halt,
+};
 
+struct pv_cpu_ops pv_cpu_ops = {
         .cpuid = native_cpuid,
         .get_debugreg = native_get_debugreg,
         .set_debugreg = native_set_debugreg,
         .clts = native_clts,
         .read_cr0 = native_read_cr0,
         .write_cr0 = native_write_cr0,
-        .read_cr2 = native_read_cr2,
-        .write_cr2 = native_write_cr2,
-        .read_cr3 = native_read_cr3,
-        .write_cr3 = native_write_cr3,
         .read_cr4 = native_read_cr4,
         .read_cr4_safe = native_read_cr4_safe,
         .write_cr4 = native_write_cr4,
-        .save_fl = native_save_fl,
-        .restore_fl = native_restore_fl,
-        .irq_disable = native_irq_disable,
-        .irq_enable = native_irq_enable,
-        .safe_halt = native_safe_halt,
-        .halt = native_halt,
         .wbinvd = native_wbinvd,
         .read_msr = native_read_msr_safe,
         .write_msr = native_write_msr_safe,
         .read_tsc = native_read_tsc,
         .read_pmc = native_read_pmc,
-        .sched_clock = native_sched_clock,
-        .get_cpu_khz = native_calculate_cpu_khz,
         .load_tr_desc = native_load_tr_desc,
         .set_ldt = native_set_ldt,
         .load_gdt = native_load_gdt,
@@ -327,9 +384,19 @@ struct paravirt_ops paravirt_ops = {
         .write_idt_entry = write_dt_entry,
         .load_esp0 = native_load_esp0,
 
+        .irq_enable_sysexit = native_irq_enable_sysexit,
+        .iret = native_iret,
+
         .set_iopl_mask = native_set_iopl_mask,
         .io_delay = native_io_delay,
 
+        .lazy_mode = {
+                .enter = paravirt_nop,
+                .leave = paravirt_nop,
+        },
+};
+
+struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
         .apic_write = native_apic_write,
         .apic_write_atomic = native_apic_write_atomic,
@@ -338,11 +405,17 @@ struct paravirt_ops paravirt_ops = {
         .setup_secondary_clock = setup_secondary_APIC_clock,
         .startup_ipi_hook = paravirt_nop,
 #endif
-        .set_lazy_mode = paravirt_nop,
+};
 
+struct pv_mmu_ops pv_mmu_ops = {
         .pagetable_setup_start = native_pagetable_setup_start,
         .pagetable_setup_done = native_pagetable_setup_done,
 
+        .read_cr2 = native_read_cr2,
+        .write_cr2 = native_write_cr2,
+        .read_cr3 = native_read_cr3,
+        .write_cr3 = native_write_cr3,
+
         .flush_tlb_user = native_flush_tlb,
         .flush_tlb_kernel = native_flush_tlb_global,
         .flush_tlb_single = native_flush_tlb_single,
@@ -381,12 +454,19 @@ struct paravirt_ops paravirt_ops = {
         .make_pte = native_make_pte,
         .make_pgd = native_make_pgd,
 
-        .irq_enable_sysexit = native_irq_enable_sysexit,
-        .iret = native_iret,
-
         .dup_mmap = paravirt_nop,
         .exit_mmap = paravirt_nop,
         .activate_mm = paravirt_nop,
+
+        .lazy_mode = {
+                .enter = paravirt_nop,
+                .leave = paravirt_nop,
+        },
 };
 
-EXPORT_SYMBOL(paravirt_ops);
+EXPORT_SYMBOL_GPL(pv_time_ops);
+EXPORT_SYMBOL_GPL(pv_cpu_ops);
+EXPORT_SYMBOL_GPL(pv_mmu_ops);
+EXPORT_SYMBOL_GPL(pv_apic_ops);
+EXPORT_SYMBOL_GPL(pv_info);
+EXPORT_SYMBOL    (pv_irq_ops);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index a50b787b3bfa..5098f58063a5 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -222,10 +222,10 @@ static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen)
         return npages;
 }
 
-static inline int translate_phb(struct pci_dev* dev)
+static inline int translation_enabled(struct iommu_table *tbl)
 {
-        int disabled = bus_info[dev->bus->number].translation_disabled;
-        return !disabled;
+        /* only PHBs with translation enabled have an IOMMU table */
+        return (tbl != NULL);
 }
 
 static void iommu_range_reserve(struct iommu_table *tbl,
@@ -388,7 +388,7 @@ static void calgary_unmap_sg(struct device *dev,
         struct scatterlist *s;
         int i;
 
-        if (!translate_phb(to_pci_dev(dev)))
+        if (!translation_enabled(tbl))
                 return;
 
         for_each_sg(sglist, s, nelems, i) {
@@ -428,7 +428,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
         unsigned long entry;
         int i;
 
-        if (!translate_phb(to_pci_dev(dev)))
+        if (!translation_enabled(tbl))
                 return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
 
         for_each_sg(sg, s, nelems, i) {
@@ -474,7 +474,7 @@ static dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
         uaddr = (unsigned long)vaddr;
         npages = num_dma_pages(uaddr, size);
 
-        if (translate_phb(to_pci_dev(dev)))
+        if (translation_enabled(tbl))
                 dma_handle = iommu_alloc(tbl, vaddr, npages, direction);
         else
                 dma_handle = virt_to_bus(vaddr);
@@ -488,7 +488,7 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
         struct iommu_table *tbl = find_iommu_table(dev);
         unsigned int npages;
 
-        if (!translate_phb(to_pci_dev(dev)))
+        if (!translation_enabled(tbl))
                 return;
 
         npages = num_dma_pages(dma_handle, size);
@@ -513,7 +513,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
                 goto error;
         memset(ret, 0, size);
 
-        if (translate_phb(to_pci_dev(dev))) {
+        if (translation_enabled(tbl)) {
                 /* set up tces to cover the allocated range */
                 mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL);
                 if (mapping == bad_dma_address)
@@ -1194,7 +1194,7 @@ static int __init calgary_init(void)
 {
         int ret;
         struct pci_dev *dev = NULL;
-        void *tce_space;
+        struct calgary_bus_info *info;
 
         ret = calgary_locate_bbars();
         if (ret)
@@ -1206,12 +1206,14 @@ static int __init calgary_init(void)
                         break;
                 if (!is_cal_pci_dev(dev->device))
                         continue;
-                if (!translate_phb(dev)) {
+
+                info = &bus_info[dev->bus->number];
+                if (info->translation_disabled) {
                         calgary_init_one_nontraslated(dev);
                         continue;
                 }
-                tce_space = bus_info[dev->bus->number].tce_space;
-                if (!tce_space && !translate_empty_slots)
+
+                if (!info->tce_space && !translate_empty_slots)
                         continue;
 
                 ret = calgary_init_one(dev);
@@ -1229,11 +1231,13 @@ error:
                         break;
                 if (!is_cal_pci_dev(dev->device))
                         continue;
-                if (!translate_phb(dev)) {
+
+                info = &bus_info[dev->bus->number];
+                if (info->translation_disabled) {
                         pci_dev_put(dev);
                         continue;
                 }
-                if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots)
+                if (!info->tce_space && !translate_empty_slots)
                         continue;
 
                 calgary_disable_translation(dev);
@@ -1546,7 +1550,7 @@ static void __init calgary_fixup_one_tce_space(struct pci_dev *dev)
 static int __init calgary_fixup_tce_spaces(void)
 {
         struct pci_dev *dev = NULL;
-        void *tce_space;
+        struct calgary_bus_info *info;
 
         if (no_iommu || swiotlb || !calgary_detected)
                 return -ENODEV;
@@ -1559,11 +1563,12 @@ static int __init calgary_fixup_tce_spaces(void)
                         break;
                 if (!is_cal_pci_dev(dev->device))
                         continue;
-                if (!translate_phb(dev))
+
+                info = &bus_info[dev->bus->number];
+                if (info->translation_disabled)
                         continue;
 
-                tce_space = bus_info[dev->bus->number].tce_space;
-                if (!tce_space)
+                if (!info->tce_space)
                         continue;
 
                 calgary_fixup_one_tce_space(dev);
diff --git a/arch/x86/kernel/pci-dma_32.c b/arch/x86/kernel/pci-dma_32.c
index 0aae2f3847a5..51330321a5d3 100644
--- a/arch/x86/kernel/pci-dma_32.c
+++ b/arch/x86/kernel/pci-dma_32.c
@@ -12,7 +12,6 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <asm/io.h>
 
 struct dma_coherent_mem {
diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma_64.c
index 9576a2eb375e..b2b42bdb0a15 100644
--- a/arch/x86/kernel/pci-dma_64.c
+++ b/arch/x86/kernel/pci-dma_64.c
@@ -51,11 +51,9 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
 {
         struct page *page;
         int node;
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                node = pcibus_to_node(to_pci_dev(dev)->bus);
-        else
-#endif
+
+        node = dev_to_node(dev);
+        if (node == -1)
                 node = numa_node_id();
 
         if (node < first_node(node_online_map))
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index cfcc84e6c350..5cdfab65e93f 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -8,6 +8,7 @@
  * See Documentation/DMA-mapping.txt for the interface specification.
  * 
  * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Subject to the GNU General Public License v2 only.
  */
 
 #include <linux/types.h>
@@ -375,7 +376,8 @@ static inline int dma_map_cont(struct scatterlist *start, int nelems,
  * DMA map all entries in a scatterlist.
  * Merge chunks that have page aligned sizes into a continuous mapping. 
  */
-int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
+static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+                        int dir)
 {
         int i;
         int out;
diff --git a/arch/x86/kernel/ptrace_32.c b/arch/x86/kernel/ptrace_32.c
index 8622b9cd3e38..99102ec5fade 100644
--- a/arch/x86/kernel/ptrace_32.c
+++ b/arch/x86/kernel/ptrace_32.c
@@ -165,7 +165,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_
 
                 seg &= ~7UL;
 
-                down(&child->mm->context.sem);
+                mutex_lock(&child->mm->context.lock);
                 if (unlikely((seg >> 3) >= child->mm->context.size))
                         addr = -1L; /* bogus selector, access would fault */
                 else {
@@ -179,7 +179,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_
                                 addr &= 0xffff;
                         addr += base;
                 }
-                up(&child->mm->context.sem);
+                mutex_unlock(&child->mm->context.lock);
         }
         return addr;
 }
diff --git a/arch/x86/kernel/ptrace_64.c b/arch/x86/kernel/ptrace_64.c
index 86321ee6da93..607085f3f08a 100644
--- a/arch/x86/kernel/ptrace_64.c
+++ b/arch/x86/kernel/ptrace_64.c
@@ -103,7 +103,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r
 
                 seg &= ~7UL;
 
-                down(&child->mm->context.sem);
+                mutex_lock(&child->mm->context.lock);
                 if (unlikely((seg >> 3) >= child->mm->context.size))
                         addr = -1L; /* bogus selector, access would fault */
                 else {
@@ -117,7 +117,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r
                                 addr &= 0xffff;
                         addr += base;
                 }
-                up(&child->mm->context.sem);
+                mutex_unlock(&child->mm->context.lock);
         }
 
         return addr;
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 8159bf0be17a..5a19f0cc5b67 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -604,7 +604,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         level = cpuid_eax(1);
         if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58))
                 set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
-        if (c->x86 == 0x10)
+        if (c->x86 == 0x10 || c->x86 == 0x11)
                 set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
 
         /* Enable workaround for FXSAVE leak */
@@ -968,7 +968,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
          * applications want to get the raw CPUID data, they should access
          * /dev/cpu/<cpu_nr>/cpuid instead.
          */
-        static char *x86_cap_flags[] = {
+        static const char *const x86_cap_flags[] = {
                 /* Intel-defined */
                 "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
                 "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
@@ -1022,7 +1022,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
         };
-        static char *x86_power_flags[] = { 
+        static const char *const x86_power_flags[] = {
                 "ts",   /* temperature sensor */
                 "fid",  /* frequency id control */
                 "vid",  /* voltage id control */
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index d01d51fcce2a..0d79df3c5631 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -385,7 +385,6 @@ static int setup_frame(int sig, struct k_sigaction *ka,
         regs->edx = (unsigned long) 0;
         regs->ecx = (unsigned long) 0;
 
-        set_fs(USER_DS);
         regs->xds = __USER_DS;
         regs->xes = __USER_DS;
         regs->xss = __USER_DS;
@@ -479,7 +478,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         regs->edx = (unsigned long) &frame->info;
         regs->ecx = (unsigned long) &frame->uc;
 
-        set_fs(USER_DS);
         regs->xds = __USER_DS;
         regs->xes = __USER_DS;
         regs->xss = __USER_DS;
diff --git a/arch/x86/kernel/smp_32.c b/arch/x86/kernel/smp_32.c
index 2d35d8502029..791d9f8036ae 100644
--- a/arch/x86/kernel/smp_32.c
+++ b/arch/x86/kernel/smp_32.c
@@ -342,6 +342,7 @@ fastcall void smp_invalidate_interrupt(struct pt_regs *regs)
         smp_mb__after_clear_bit();
 out:
         put_cpu_no_resched();
+        __get_cpu_var(irq_stat).irq_tlb_count++;
 }
 
 void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
@@ -640,6 +641,7 @@ static void native_smp_send_stop(void)
 fastcall void smp_reschedule_interrupt(struct pt_regs *regs)
 {
         ack_APIC_irq();
+        __get_cpu_var(irq_stat).irq_resched_count++;
 }
 
 fastcall void smp_call_function_interrupt(struct pt_regs *regs)
@@ -660,6 +662,7 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs)
          */
         irq_enter();
         (*func)(info);
+        __get_cpu_var(irq_stat).irq_call_count++;
         irq_exit();
 
         if (wait) {
@@ -705,3 +708,10 @@ struct smp_ops smp_ops = {
         .smp_send_reschedule = native_smp_send_reschedule,
         .smp_call_function_mask = native_smp_call_function_mask,
 };
+
+int smp_call_function_mask(cpumask_t mask, void (*func) (void *info),
+                           void *info, int wait)
+{
+        return smp_ops.smp_call_function_mask(mask, func, info, wait);
+}
+EXPORT_SYMBOL(smp_call_function_mask);
diff --git a/arch/x86/kernel/smp_64.c b/arch/x86/kernel/smp_64.c
index df4a82812adb..5c2964727d19 100644
--- a/arch/x86/kernel/smp_64.c
+++ b/arch/x86/kernel/smp_64.c
@@ -163,6 +163,7 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
 out:
         ack_APIC_irq();
         cpu_clear(cpu, f->flush_cpumask);
+        add_pda(irq_tlb_count, 1);
 }
 
 static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
@@ -493,6 +494,7 @@ void smp_send_stop(void)
 asmlinkage void smp_reschedule_interrupt(void)
 {
         ack_APIC_irq();
+        add_pda(irq_resched_count, 1);
 }
 
 asmlinkage void smp_call_function_interrupt(void)
@@ -514,6 +516,7 @@ asmlinkage void smp_call_function_interrupt(void)
         exit_idle();
         irq_enter();
         (*func)(info);
+        add_pda(irq_call_count, 1);
         irq_exit();
         if (wait) {
                 mb();
diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c
index 31fc08bd15ef..be3faac04719 100644
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -102,8 +102,8 @@ u8 apicid_2_node[MAX_APICID];
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data [];
-extern unsigned char trampoline_end  [];
+extern const unsigned char trampoline_data [];
+extern const unsigned char trampoline_end  [];
 static unsigned char *trampoline_base;
 static int trampoline_exec;
 
@@ -118,7 +118,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 };
  * has made sure it's suitably aligned.
  */
 
-static unsigned long __devinit setup_trampoline(void)
+static unsigned long __cpuinit setup_trampoline(void)
 {
         memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data);
         return virt_to_phys(trampoline_base);
@@ -1021,6 +1021,12 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
         if (!max_cpus) {
                 smp_found_config = 0;
                 printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
+
+                if (nmi_watchdog == NMI_LOCAL_APIC) {
+                        printk(KERN_INFO "activating minimal APIC for NMI watchdog use.\n");
+                        connect_bsp_APIC();
+                        setup_local_APIC();
+                }
                 smpboot_clear_io_apic_irqs();
                 phys_cpu_present_map = physid_mask_of_physid(0);
                 cpu_set(0, per_cpu(cpu_sibling_map, 0));
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 0faa0a0af272..e351ac4ab5b1 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -102,8 +102,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data[];
-extern unsigned char trampoline_end[];
+extern const unsigned char trampoline_data[];
+extern const unsigned char trampoline_end[];
 
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -695,7 +695,6 @@ do_rest:
                 cpu_clear(cpu, cpu_present_map);
                 cpu_clear(cpu, cpu_possible_map);
                 x86_cpu_to_apicid[cpu] = BAD_APICID;
-                x86_cpu_to_log_apicid[cpu] = BAD_APICID;
                 return -EIO;
         }
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 413e527cdeb9..6fa6cf036c70 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -33,7 +33,7 @@ static void save_stack_address(void *data, unsigned long addr)
                 trace->entries[trace->nr_entries++] = addr;
 }
 
-static struct stacktrace_ops save_stack_ops = {
+static const struct stacktrace_ops save_stack_ops = {
         .warning = save_stack_warning,
         .warning_symbol = save_stack_warning_symbol,
         .stack = save_stack_stack,
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index e3f2569b2c44..9e540fee7009 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -40,9 +40,9 @@ static inline void flush_tce(void* tceaddr)
 {
         /* a single tce can't cross a cache line */
         if (cpu_has_clflush)
-                asm volatile("clflush (%0)" :: "r" (tceaddr));
+                clflush(tceaddr);
         else
-                asm volatile("wbinvd":::"memory");
+                wbinvd();
 }
 
 void tce_build(struct iommu_table *tbl, unsigned long index,
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index c25f23eb397c..8caa0b777466 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -44,15 +44,15 @@ int arch_register_cpu(int num)
          * Also certain PCI quirks require not to enable hotplug control
          * for all CPU's.
          */
-        if (num && enable_cpu_hotplug)
+#ifdef CONFIG_HOTPLUG_CPU
+        if (num)
                 cpu_devices[num].cpu.hotpluggable = 1;
+#endif
 
         return register_cpu(&cpu_devices[num].cpu, num);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int enable_cpu_hotplug = 1;
-
 void arch_unregister_cpu(int num) {
         return unregister_cpu(&cpu_devices[num].cpu);
 }
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
index f62815f8d06a..9bcc1c6aca3d 100644
--- a/arch/x86/kernel/trampoline_32.S
+++ b/arch/x86/kernel/trampoline_32.S
@@ -36,11 +36,11 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 
-.data
-
 /* We can free up trampoline after bootup if cpu hotplug is not supported. */
 #ifndef CONFIG_HOTPLUG_CPU
 .section ".init.data","aw",@progbits
+#else
+.section .rodata,"a",@progbits
 #endif
 
 .code16
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 607983b0d27b..e30b67c6a9f5 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -33,7 +33,12 @@
 #include <asm/msr.h>
 #include <asm/segment.h>
 
-.data
+/* We can free up trampoline after bootup if cpu hotplug is not supported. */
+#ifndef CONFIG_HOTPLUG_CPU
+.section .init.data, "aw", @progbits
+#else
+.section .rodata, "a", @progbits
+#endif
 
 .code16
 
diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index 05c27ecaf2a7..b132d3957dfc 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -112,7 +112,7 @@ struct stack_frame {
 
 static inline unsigned long print_context_stack(struct thread_info *tinfo,
                                 unsigned long *stack, unsigned long ebp,
-                                struct stacktrace_ops *ops, void *data)
+                                const struct stacktrace_ops *ops, void *data)
 {
 #ifdef  CONFIG_FRAME_POINTER
         struct stack_frame *frame = (struct stack_frame *)ebp;
@@ -149,7 +149,7 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack,
-                struct stacktrace_ops *ops, void *data)
+                const struct stacktrace_ops *ops, void *data)
 {
         unsigned long ebp = 0;
 
@@ -221,7 +221,7 @@ static void print_trace_address(void *data, unsigned long addr)
         touch_nmi_watchdog();
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
         .warning = print_trace_warning,
         .warning_symbol = print_trace_warning_symbol,
         .stack = print_trace_stack,
@@ -398,31 +398,24 @@ void die(const char * str, struct pt_regs * regs, long err)
                 local_save_flags(flags);
 
         if (++die.lock_owner_depth < 3) {
-                int nl = 0;
                 unsigned long esp;
                 unsigned short ss;
 
                 report_bug(regs->eip, regs);
 
-                printk(KERN_EMERG "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
+                printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff,
+                       ++die_counter);
 #ifdef CONFIG_PREEMPT
-                printk(KERN_EMERG "PREEMPT ");
-                nl = 1;
+                printk("PREEMPT ");
 #endif
 #ifdef CONFIG_SMP
-                if (!nl)
-                        printk(KERN_EMERG);
                 printk("SMP ");
-                nl = 1;
 #endif
 #ifdef CONFIG_DEBUG_PAGEALLOC
-                if (!nl)
-                        printk(KERN_EMERG);
                 printk("DEBUG_PAGEALLOC");
-                nl = 1;
 #endif
-                if (nl)
-                        printk("\n");
+                printk("\n");
+
                 if (notify_die(DIE_OOPS, str, regs, err,
                                         current->thread.trap_no, SIGSEGV) !=
                                 NOTIFY_STOP) {
@@ -1112,20 +1105,6 @@ asmlinkage void math_emulate(long arg)
 
 #endif /* CONFIG_MATH_EMULATION */
 
-#ifdef CONFIG_X86_F00F_BUG
-void __init trap_init_f00f_bug(void)
-{
-        __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
-
-        /*
-         * Update the IDT descriptor and reload the IDT so that
-         * it uses the read-only mapped virtual address.
-         */
-        idt_descr.address = fix_to_virt(FIX_F00F_IDT);
-        load_idt(&idt_descr);
-}
-#endif
-
 /*
  * This needs to use 'idt_table' rather than 'idt', and
  * thus use the _nonmapped_ version of the IDT, as the
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index bc7116acf8ff..b4a9b3db1994 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -215,7 +215,7 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
                 unsigned long *stack,
-                struct stacktrace_ops *ops, void *data)
+                const struct stacktrace_ops *ops, void *data)
 {
         const unsigned cpu = get_cpu();
         unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;
@@ -336,7 +336,7 @@ static void print_trace_address(void *data, unsigned long addr)
         printk_address(addr);
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
         .warning = print_trace_warning,
         .warning_symbol = print_trace_warning_symbol,
         .stack = print_trace_stack,
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index b85ad754f70e..e87a3939ed40 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -349,10 +349,10 @@ __cpuinit int unsynchronized_tsc(void)
 
 static void __init check_geode_tsc_reliable(void)
 {
-        unsigned long val;
+        unsigned long res_low, res_high;
 
-        rdmsrl(MSR_GEODE_BUSCONT_CONF0, val);
-        if ((val & RTSC_SUSP))
+        rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+        if (res_low & RTSC_SUSP)
                 clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 }
 #else
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 18673e0f193b..f02bad68abaa 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -134,21 +134,21 @@ static unsigned vmi_patch(u8 type, u16 clobbers, void *insns,
                           unsigned long eip, unsigned len)
 {
         switch (type) {
-                case PARAVIRT_PATCH(irq_disable):
+                case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
                         return patch_internal(VMI_CALL_DisableInterrupts, len,
                                               insns, eip);
-                case PARAVIRT_PATCH(irq_enable):
+                case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
                         return patch_internal(VMI_CALL_EnableInterrupts, len,
                                               insns, eip);
-                case PARAVIRT_PATCH(restore_fl):
+                case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
                         return patch_internal(VMI_CALL_SetInterruptMask, len,
                                               insns, eip);
-                case PARAVIRT_PATCH(save_fl):
+                case PARAVIRT_PATCH(pv_irq_ops.save_fl):
                         return patch_internal(VMI_CALL_GetInterruptMask, len,
                                               insns, eip);
-                case PARAVIRT_PATCH(iret):
+                case PARAVIRT_PATCH(pv_cpu_ops.iret):
                         return patch_internal(VMI_CALL_IRET, len, insns, eip);
-                case PARAVIRT_PATCH(irq_enable_sysexit):
+                case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit):
                         return patch_internal(VMI_CALL_SYSEXIT, len, insns, eip);
                 default:
                         break;
@@ -552,24 +552,22 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_set_lazy_mode(enum paravirt_lazy_mode mode)
+static void vmi_enter_lazy_cpu(void)
 {
-        static DEFINE_PER_CPU(enum paravirt_lazy_mode, lazy_mode);
-
-        if (!vmi_ops.set_lazy_mode)
-                return;
+        paravirt_enter_lazy_cpu();
+        vmi_ops.set_lazy_mode(2);
+}
 
-        /* Modes should never nest or overlap */
-        BUG_ON(__get_cpu_var(lazy_mode) && !(mode == PARAVIRT_LAZY_NONE ||
-                                             mode == PARAVIRT_LAZY_FLUSH));
+static void vmi_enter_lazy_mmu(void)
+{
+        paravirt_enter_lazy_mmu();
+        vmi_ops.set_lazy_mode(1);
+}
 
-        if (mode == PARAVIRT_LAZY_FLUSH) {
-                vmi_ops.set_lazy_mode(0);
-                vmi_ops.set_lazy_mode(__get_cpu_var(lazy_mode));
-        } else {
-                vmi_ops.set_lazy_mode(mode);
-                __get_cpu_var(lazy_mode) = mode;
-        }
+static void vmi_leave_lazy(void)
+{
+        paravirt_leave_lazy(paravirt_get_lazy_mode());
+        vmi_ops.set_lazy_mode(0);
 }
 
 static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -690,9 +688,9 @@ do {								\
         reloc = call_vrom_long_func(vmi_rom, get_reloc,         \
                                     VMI_CALL_##vmicall);        \
         if (rel->type == VMI_RELOCATION_CALL_REL)               \
-                paravirt_ops.opname = (void *)rel->eip;         \
+                opname = (void *)rel->eip;                      \
         else if (rel->type == VMI_RELOCATION_NOP)               \
-                paravirt_ops.opname = (void *)vmi_nop;          \
+                opname = (void *)vmi_nop;                       \
         else if (rel->type != VMI_RELOCATION_NONE)              \
                 printk(KERN_WARNING "VMI: Unknown relocation "  \
                                     "type %d for " #vmicall"\n",\
@@ -712,7 +710,7 @@ do {								\
                                     VMI_CALL_##vmicall);        \
         BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);           \
         if (rel->type == VMI_RELOCATION_CALL_REL) {             \
-                paravirt_ops.opname = wrapper;                  \
+                opname = wrapper;                               \
                 vmi_ops.cache = (void *)rel->eip;               \
         }                                                       \
 } while (0)
@@ -732,11 +730,11 @@ static inline int __init activate_vmi(void)
         }
         savesegment(cs, kernel_cs);
 
-        paravirt_ops.paravirt_enabled = 1;
-        paravirt_ops.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
+        pv_info.paravirt_enabled = 1;
+        pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
+        pv_info.name = "vmi";
 
-        paravirt_ops.patch = vmi_patch;
-        paravirt_ops.name = "vmi";
+        pv_init_ops.patch = vmi_patch;
 
         /*
          * Many of these operations are ABI compatible with VMI.
@@ -754,26 +752,26 @@ static inline int __init activate_vmi(void)
          */
 
         /* CPUID is special, so very special it gets wrapped like a present */
-        para_wrap(cpuid, vmi_cpuid, cpuid, CPUID);
-
-        para_fill(clts, CLTS);
-        para_fill(get_debugreg, GetDR);
-        para_fill(set_debugreg, SetDR);
-        para_fill(read_cr0, GetCR0);
-        para_fill(read_cr2, GetCR2);
-        para_fill(read_cr3, GetCR3);
-        para_fill(read_cr4, GetCR4);
-        para_fill(write_cr0, SetCR0);
-        para_fill(write_cr2, SetCR2);
-        para_fill(write_cr3, SetCR3);
-        para_fill(write_cr4, SetCR4);
-        para_fill(save_fl, GetInterruptMask);
-        para_fill(restore_fl, SetInterruptMask);
-        para_fill(irq_disable, DisableInterrupts);
-        para_fill(irq_enable, EnableInterrupts);
-
-        para_fill(wbinvd, WBINVD);
-        para_fill(read_tsc, RDTSC);
+        para_wrap(pv_cpu_ops.cpuid, vmi_cpuid, cpuid, CPUID);
+
+        para_fill(pv_cpu_ops.clts, CLTS);
+        para_fill(pv_cpu_ops.get_debugreg, GetDR);
+        para_fill(pv_cpu_ops.set_debugreg, SetDR);
+        para_fill(pv_cpu_ops.read_cr0, GetCR0);
+        para_fill(pv_mmu_ops.read_cr2, GetCR2);
+        para_fill(pv_mmu_ops.read_cr3, GetCR3);
+        para_fill(pv_cpu_ops.read_cr4, GetCR4);
+        para_fill(pv_cpu_ops.write_cr0, SetCR0);
+        para_fill(pv_mmu_ops.write_cr2, SetCR2);
+        para_fill(pv_mmu_ops.write_cr3, SetCR3);
+        para_fill(pv_cpu_ops.write_cr4, SetCR4);
+        para_fill(pv_irq_ops.save_fl, GetInterruptMask);
+        para_fill(pv_irq_ops.restore_fl, SetInterruptMask);
+        para_fill(pv_irq_ops.irq_disable, DisableInterrupts);
+        para_fill(pv_irq_ops.irq_enable, EnableInterrupts);
+
+        para_fill(pv_cpu_ops.wbinvd, WBINVD);
+        para_fill(pv_cpu_ops.read_tsc, RDTSC);
 
         /* The following we emulate with trap and emulate for now */
         /* paravirt_ops.read_msr = vmi_rdmsr */
@@ -781,29 +779,38 @@ static inline int __init activate_vmi(void)
         /* paravirt_ops.rdpmc = vmi_rdpmc */
 
         /* TR interface doesn't pass TR value, wrap */
-        para_wrap(load_tr_desc, vmi_set_tr, set_tr, SetTR);
+        para_wrap(pv_cpu_ops.load_tr_desc, vmi_set_tr, set_tr, SetTR);
 
         /* LDT is special, too */
-        para_wrap(set_ldt, vmi_set_ldt, _set_ldt, SetLDT);
-
-        para_fill(load_gdt, SetGDT);
-        para_fill(load_idt, SetIDT);
-        para_fill(store_gdt, GetGDT);
-        para_fill(store_idt, GetIDT);
-        para_fill(store_tr, GetTR);
-        paravirt_ops.load_tls = vmi_load_tls;
-        para_fill(write_ldt_entry, WriteLDTEntry);
-        para_fill(write_gdt_entry, WriteGDTEntry);
-        para_fill(write_idt_entry, WriteIDTEntry);
-        para_wrap(load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack);
-        para_fill(set_iopl_mask, SetIOPLMask);
-        para_fill(io_delay, IODelay);
-        para_wrap(set_lazy_mode, vmi_set_lazy_mode, set_lazy_mode, SetLazyMode);
+        para_wrap(pv_cpu_ops.set_ldt, vmi_set_ldt, _set_ldt, SetLDT);
+
+        para_fill(pv_cpu_ops.load_gdt, SetGDT);
+        para_fill(pv_cpu_ops.load_idt, SetIDT);
+        para_fill(pv_cpu_ops.store_gdt, GetGDT);
+        para_fill(pv_cpu_ops.store_idt, GetIDT);
+        para_fill(pv_cpu_ops.store_tr, GetTR);
+        pv_cpu_ops.load_tls = vmi_load_tls;
+        para_fill(pv_cpu_ops.write_ldt_entry, WriteLDTEntry);
+        para_fill(pv_cpu_ops.write_gdt_entry, WriteGDTEntry);
+        para_fill(pv_cpu_ops.write_idt_entry, WriteIDTEntry);
+        para_wrap(pv_cpu_ops.load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack);
+        para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
+        para_fill(pv_cpu_ops.io_delay, IODelay);
+
+        para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+                  set_lazy_mode, SetLazyMode);
+        para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+                  set_lazy_mode, SetLazyMode);
+
+        para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
+                  set_lazy_mode, SetLazyMode);
+        para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+                  set_lazy_mode, SetLazyMode);
 
         /* user and kernel flush are just handled with different flags to FlushTLB */
-        para_wrap(flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
-        para_wrap(flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
-        para_fill(flush_tlb_single, InvalPage);
+        para_wrap(pv_mmu_ops.flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
+        para_wrap(pv_mmu_ops.flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
+        para_fill(pv_mmu_ops.flush_tlb_single, InvalPage);
 
         /*
          * Until a standard flag format can be agreed on, we need to
@@ -819,41 +826,41 @@ static inline int __init activate_vmi(void)
 #endif
 
         if (vmi_ops.set_pte) {
-                paravirt_ops.set_pte = vmi_set_pte;
-                paravirt_ops.set_pte_at = vmi_set_pte_at;
-                paravirt_ops.set_pmd = vmi_set_pmd;
+                pv_mmu_ops.set_pte = vmi_set_pte;
+                pv_mmu_ops.set_pte_at = vmi_set_pte_at;
+                pv_mmu_ops.set_pmd = vmi_set_pmd;
 #ifdef CONFIG_X86_PAE
-                paravirt_ops.set_pte_atomic = vmi_set_pte_atomic;
-                paravirt_ops.set_pte_present = vmi_set_pte_present;
-                paravirt_ops.set_pud = vmi_set_pud;
-                paravirt_ops.pte_clear = vmi_pte_clear;
-                paravirt_ops.pmd_clear = vmi_pmd_clear;
+                pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic;
+                pv_mmu_ops.set_pte_present = vmi_set_pte_present;
+                pv_mmu_ops.set_pud = vmi_set_pud;
+                pv_mmu_ops.pte_clear = vmi_pte_clear;
+                pv_mmu_ops.pmd_clear = vmi_pmd_clear;
 #endif
         }
 
         if (vmi_ops.update_pte) {
-                paravirt_ops.pte_update = vmi_update_pte;
-                paravirt_ops.pte_update_defer = vmi_update_pte_defer;
+                pv_mmu_ops.pte_update = vmi_update_pte;
+                pv_mmu_ops.pte_update_defer = vmi_update_pte_defer;
         }
 
         vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
         if (vmi_ops.allocate_page) {
-                paravirt_ops.alloc_pt = vmi_allocate_pt;
-                paravirt_ops.alloc_pd = vmi_allocate_pd;
-                paravirt_ops.alloc_pd_clone = vmi_allocate_pd_clone;
+                pv_mmu_ops.alloc_pt = vmi_allocate_pt;
+                pv_mmu_ops.alloc_pd = vmi_allocate_pd;
+                pv_mmu_ops.alloc_pd_clone = vmi_allocate_pd_clone;
         }
 
         vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
         if (vmi_ops.release_page) {
-                paravirt_ops.release_pt = vmi_release_pt;
-                paravirt_ops.release_pd = vmi_release_pd;
+                pv_mmu_ops.release_pt = vmi_release_pt;
+                pv_mmu_ops.release_pd = vmi_release_pd;
         }
 
         /* Set linear is needed in all cases */
         vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
 #ifdef CONFIG_HIGHPTE
         if (vmi_ops.set_linear_mapping)
-                paravirt_ops.kmap_atomic_pte = vmi_kmap_atomic_pte;
+                pv_mmu_ops.kmap_atomic_pte = vmi_kmap_atomic_pte;
 #endif
 
         /*
@@ -863,17 +870,17 @@ static inline int __init activate_vmi(void)
          * the backend.  They are performance critical anyway, so requiring
          * a patch is not a big problem.
          */
-        paravirt_ops.irq_enable_sysexit = (void *)0xfeedbab0;
-        paravirt_ops.iret = (void *)0xbadbab0;
+        pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0;
+        pv_cpu_ops.iret = (void *)0xbadbab0;
 
 #ifdef CONFIG_SMP
-        para_wrap(startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState);
+        para_wrap(pv_apic_ops.startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState);
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
-        para_fill(apic_read, APICRead);
-        para_fill(apic_write, APICWrite);
-        para_fill(apic_write_atomic, APICWrite);
+        para_fill(pv_apic_ops.apic_read, APICRead);
+        para_fill(pv_apic_ops.apic_write, APICWrite);
+        para_fill(pv_apic_ops.apic_write_atomic, APICWrite);
 #endif
 
         /*
@@ -891,15 +898,15 @@ static inline int __init activate_vmi(void)
                 vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
                 vmi_timer_ops.cancel_alarm =
                          vmi_get_function(VMI_CALL_CancelAlarm);
-                paravirt_ops.time_init = vmi_time_init;
-                paravirt_ops.get_wallclock = vmi_get_wallclock;
-                paravirt_ops.set_wallclock = vmi_set_wallclock;
+                pv_time_ops.time_init = vmi_time_init;
+                pv_time_ops.get_wallclock = vmi_get_wallclock;
+                pv_time_ops.set_wallclock = vmi_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-                paravirt_ops.setup_boot_clock = vmi_time_bsp_init;
-                paravirt_ops.setup_secondary_clock = vmi_time_ap_init;
+                pv_apic_ops.setup_boot_clock = vmi_time_bsp_init;
+                pv_apic_ops.setup_secondary_clock = vmi_time_ap_init;
 #endif
-                paravirt_ops.sched_clock = vmi_sched_clock;
-                paravirt_ops.get_cpu_khz = vmi_cpu_khz;
+                pv_time_ops.sched_clock = vmi_sched_clock;
+                pv_time_ops.get_cpu_khz = vmi_cpu_khz;
 
                 /* We have true wallclock functions; disable CMOS clock sync */
                 no_sync_cmos_clock = 1;
@@ -908,7 +915,7 @@ static inline int __init activate_vmi(void)
                 disable_vmi_timer = 1;
         }
 
-        para_fill(safe_halt, Halt);
+        para_fill(pv_irq_ops.safe_halt, Halt);
 
         /*
          * Alternative instruction rewriting doesn't happen soon enough
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 93847d848157..8a67e282cb5e 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -78,7 +78,6 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
         vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
         vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
         vsyscall_gtod_data.sys_tz = sys_tz;
-        vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
         vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
         write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
@@ -289,7 +288,7 @@ static void __cpuinit vsyscall_set_cpu(int cpu)
         unsigned long *d;
         unsigned long node = 0;
 #ifdef CONFIG_NUMA
-        node = cpu_to_node[cpu];
+        node = cpu_to_node(cpu);
 #endif
         if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP))
                 write_rdtscp_aux((node << 12) | cpu);
diff --git a/arch/x86/lib/bitstr_64.c b/arch/x86/lib/bitstr_64.c
index 24676609a6ac..7445caf1b5de 100644
--- a/arch/x86/lib/bitstr_64.c
+++ b/arch/x86/lib/bitstr_64.c
@@ -14,7 +14,7 @@ find_next_zero_string(unsigned long *bitmap, long start, long nbits, int len)
         
         /* could test bitsliced, but it's hardly worth it */
         end = n+len;
-        if (end >= nbits) 
+        if (end > nbits)
                 return -1; 
         for (i = n+1; i < end; i++) { 
                 if (test_bit(i, bitmap)) {  
diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
index 7767962f25d3..57d043fa893e 100644
--- a/arch/x86/lib/msr-on-cpu.c
+++ b/arch/x86/lib/msr-on-cpu.c
@@ -26,27 +26,18 @@ static void __rdmsr_safe_on_cpu(void *info)
 static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
 {
         int err = 0;
-        preempt_disable();
-        if (smp_processor_id() == cpu)
-                if (safe)
-                        err = rdmsr_safe(msr_no, l, h);
-                else
-                        rdmsr(msr_no, *l, *h);
-        else {
-                struct msr_info rv;
-
-                rv.msr_no = msr_no;
-                if (safe) {
-                        smp_call_function_single(cpu, __rdmsr_safe_on_cpu,
-                                                 &rv, 0, 1);
-                        err = rv.err;
-                } else {
-                        smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
-                }
-                *l = rv.l;
-                *h = rv.h;
+        struct msr_info rv;
+
+        rv.msr_no = msr_no;
+        if (safe) {
+                smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 0, 1);
+                err = rv.err;
+        } else {
+                smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
         }
-        preempt_enable();
+        *l = rv.l;
+        *h = rv.h;
+
         return err;
 }
 
@@ -67,27 +58,18 @@ static void __wrmsr_safe_on_cpu(void *info)
 static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
 {
         int err = 0;
-        preempt_disable();
-        if (smp_processor_id() == cpu)
-                if (safe)
-                        err = wrmsr_safe(msr_no, l, h);
-                else
-                        wrmsr(msr_no, l, h);
-        else {
-                struct msr_info rv;
-
-                rv.msr_no = msr_no;
-                rv.l = l;
-                rv.h = h;
-                if (safe) {
-                        smp_call_function_single(cpu, __wrmsr_safe_on_cpu,
-                                                 &rv, 0, 1);
-                        err = rv.err;
-                } else {
-                        smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
-                }
+        struct msr_info rv;
+
+        rv.msr_no = msr_no;
+        rv.l = l;
+        rv.h = h;
+        if (safe) {
+                smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 0, 1);
+                err = rv.err;
+        } else {
+                smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
         }
-        preempt_enable();
+
         return err;
 }
 
diff --git a/arch/x86/lib/rwlock_64.S b/arch/x86/lib/rwlock_64.S
index 0cde1f807314..05ea55f71405 100644
--- a/arch/x86/lib/rwlock_64.S
+++ b/arch/x86/lib/rwlock_64.S
@@ -2,7 +2,7 @@
 
 #include <linux/linkage.h>
 #include <asm/rwlock.h>
-#include <asm/alternative-asm.i>
+#include <asm/alternative-asm.h>
 #include <asm/dwarf2.h>
 
 /* rdi: pointer to rwlock_t */
diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S
index c01eb39c0b43..444fba400983 100644
--- a/arch/x86/lib/semaphore_32.S
+++ b/arch/x86/lib/semaphore_32.S
@@ -15,8 +15,8 @@
 
 #include <linux/linkage.h>
 #include <asm/rwlock.h>
-#include <asm/alternative-asm.i>
-#include <asm/frame.i>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
 #include <asm/dwarf2.h>
 
 /*
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 2c773fefa3dd..c2c0504a3071 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -160,26 +160,6 @@ char *strchr(const char * s, int c)
 EXPORT_SYMBOL(strchr);
 #endif
 
-#ifdef __HAVE_ARCH_STRRCHR
-char *strrchr(const char * s, int c)
-{
-        int d0, d1;
-        char * res;
-        asm volatile( "movb %%al,%%ah\n"
-                "1:\tlodsb\n\t"
-                "cmpb %%ah,%%al\n\t"
-                "jne 2f\n\t"
-                "leal -1(%%esi),%0\n"
-                "2:\ttestb %%al,%%al\n\t"
-                "jne 1b"
-                :"=g" (res), "=&S" (d0), "=&a" (d1)
-                :"0" (0),"1" (s),"2" (c)
-                :"memory");
-        return res;
-}
-EXPORT_SYMBOL(strrchr);
-#endif
-
 #ifdef __HAVE_ARCH_STRLEN
 size_t strlen(const char * s)
 {
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index 1bd82983986d..3f08010f3517 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -35,7 +35,11 @@ void __init pre_intr_init_hook(void)
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
  */
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+        .handler = no_action,
+        .mask = CPU_MASK_NONE,
+        .name = "cascade",
+};
 
 /**
  * intr_init_hook - post gate setup interrupt initialisation
diff --git a/arch/x86/mach-es7000/es7000plat.c b/arch/x86/mach-es7000/es7000plat.c
index ab99072d3f9a..f5d6f7d8b86e 100644
--- a/arch/x86/mach-es7000/es7000plat.c
+++ b/arch/x86/mach-es7000/es7000plat.c
@@ -46,11 +46,11 @@
  * ES7000 Globals
  */
 
-volatile unsigned long  *psai = NULL;
-struct mip_reg          *mip_reg;
-struct mip_reg          *host_reg;
-int                     mip_port;
-unsigned long           mip_addr, host_addr;
+static volatile unsigned long   *psai = NULL;
+static struct mip_reg           *mip_reg;
+static struct mip_reg           *host_reg;
+static int                      mip_port;
+static unsigned long            mip_addr, host_addr;
 
 /*
  * GSI override for ES7000 platforms.
@@ -288,28 +288,8 @@ es7000_start_cpu(int cpu, unsigned long eip)
 
 }
 
-int
-es7000_stop_cpu(int cpu)
-{
-        int startup;
-
-        if (psai == NULL)
-                return -1;
-
-        startup= (0x1000000 | cpu);
-
-        while ((*psai & 0xff00ffff) != startup)
-                ;
-
-        startup = (*psai & 0xff0000) >> 16;
-        *psai &= 0xffffff;
-
-        return 0;
-
-}
-
 void __init
-es7000_sw_apic()
+es7000_sw_apic(void)
 {
         if (es7000_plat) {
                 int mip_status;
diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c
index 74f3da634423..4121d1551800 100644
--- a/arch/x86/mach-generic/probe.c
+++ b/arch/x86/mach-generic/probe.c
@@ -22,7 +22,7 @@ extern struct genapic apic_default;
 
 struct genapic *genapic = &apic_default;
 
-struct genapic *apic_probe[] __initdata = { 
+static struct genapic *apic_probe[] __initdata = {
         &apic_summit,
         &apic_bigsmp, 
         &apic_es7000,
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index a0ab4002abcd..3bef977cb29b 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -18,7 +18,11 @@ void __init pre_intr_init_hook(void)
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
  */
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+        .handler = no_action,
+        .mask = CPU_MASK_NONE,
+        .name = "cascade",
+};
 
 void __init intr_init_hook(void)
 {
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index b87f8548e75a..e4928aa6bdfb 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -442,8 +442,8 @@ static __u32 __init
 setup_trampoline(void)
 {
         /* these two are global symbols in trampoline.S */
-        extern __u8 trampoline_end[];
-        extern __u8 trampoline_data[];
+        extern const __u8 trampoline_end[];
+        extern const __u8 trampoline_data[];
 
         memcpy((__u8 *)trampoline_base, trampoline_data,
                trampoline_end - trampoline_data);
@@ -1037,6 +1037,7 @@ smp_call_function_interrupt(void)
          */
         irq_enter();
         (*func)(info);
+        __get_cpu_var(irq_stat).irq_call_count++;
         irq_exit();
         if (wait) {
                 mb();
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index b1e45457d4ef..13893772cc48 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -103,14 +103,14 @@ extern unsigned long highend_pfn, highstart_pfn;
 
 #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
 
-unsigned long node_remap_start_pfn[MAX_NUMNODES];
+static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 unsigned long node_remap_size[MAX_NUMNODES];
-unsigned long node_remap_offset[MAX_NUMNODES];
-void *node_remap_start_vaddr[MAX_NUMNODES];
+static unsigned long node_remap_offset[MAX_NUMNODES];
+static void *node_remap_start_vaddr[MAX_NUMNODES];
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-void *node_remap_end_vaddr[MAX_NUMNODES];
-void *node_remap_alloc_vaddr[MAX_NUMNODES];
+static void *node_remap_end_vaddr[MAX_NUMNODES];
+static void *node_remap_alloc_vaddr[MAX_NUMNODES];
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
 /*
diff --git a/arch/x86/mm/fault_32.c b/arch/x86/mm/fault_32.c
index c686ae20fd6b..6555c3d14371 100644
--- a/arch/x86/mm/fault_32.c
+++ b/arch/x86/mm/fault_32.c
@@ -105,7 +105,7 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs,
            LDT and other horrors are only used in user space. */
         if (seg & (1<<2)) {
                 /* Must lock the LDT while reading it. */
-                down(&current->mm->context.sem);
+                mutex_lock(&current->mm->context.lock);
                 desc = current->mm->context.ldt;
                 desc = (void *)desc + (seg & ~7);
         } else {
@@ -118,7 +118,7 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs,
         base = get_desc_base((unsigned long *)desc);
 
         if (seg & (1<<2)) { 
-                up(&current->mm->context.sem);
+                mutex_unlock(&current->mm->context.lock);
         } else
                 put_cpu();
 
@@ -539,23 +539,22 @@ no_context:
                         printk(KERN_ALERT "BUG: unable to handle kernel paging"
                                         " request");
                 printk(" at virtual address %08lx\n",address);
-                printk(KERN_ALERT " printing eip:\n");
-                printk("%08lx\n", regs->eip);
+                printk(KERN_ALERT "printing eip: %08lx ", regs->eip);
 
                 page = read_cr3();
                 page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
 #ifdef CONFIG_X86_PAE
-                printk(KERN_ALERT "*pdpt = %016Lx\n", page);
+                printk("*pdpt = %016Lx ", page);
                 if ((page >> PAGE_SHIFT) < max_low_pfn
                     && page & _PAGE_PRESENT) {
                         page &= PAGE_MASK;
                         page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
                                                                  & (PTRS_PER_PMD - 1)];
-                        printk(KERN_ALERT "*pde = %016Lx\n", page);
+                        printk(KERN_ALERT "*pde = %016Lx ", page);
                         page &= ~_PAGE_NX;
                 }
 #else
-                printk(KERN_ALERT "*pde = %08lx\n", page);
+                printk("*pde = %08lx ", page);
 #endif
 
                 /*
@@ -569,8 +568,10 @@ no_context:
                         page &= PAGE_MASK;
                         page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
                                                                  & (PTRS_PER_PTE - 1)];
-                        printk(KERN_ALERT "*pte = %0*Lx\n", sizeof(page)*2, (u64)page);
+                        printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
                 }
+
+                printk("\n");
         }
 
         tsk->thread.cr2 = address;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index dda4e83649a0..c7d19471261d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -85,13 +85,20 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
         if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
-                pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+                pte_t *page_table = NULL;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+                page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
+#endif
+                if (!page_table)
+                        page_table =
+                                (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 
                 paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
                 set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
                 BUG_ON(page_table != pte_offset_kernel(pmd, 0));
         }
-        
+
         return pte_offset_kernel(pmd, 0);
 }
 
@@ -741,24 +748,12 @@ struct kmem_cache *pmd_cache;
 
 void __init pgtable_cache_init(void)
 {
-        size_t pgd_size = PTRS_PER_PGD*sizeof(pgd_t);
-
-        if (PTRS_PER_PMD > 1) {
+        if (PTRS_PER_PMD > 1)
                 pmd_cache = kmem_cache_create("pmd",
-                                        PTRS_PER_PMD*sizeof(pmd_t),
-                                        PTRS_PER_PMD*sizeof(pmd_t),
-                                        SLAB_PANIC,
-                                        pmd_ctor);
-                if (!SHARED_KERNEL_PMD) {
-                        /* If we're in PAE mode and have a non-shared
-                           kernel pmd, then the pgd size must be a
-                           page size.  This is because the pgd_list
-                           links through the page structure, so there
-                           can only be one pgd per page for this to
-                           work. */
-                        pgd_size = PAGE_SIZE;
-                }
-        }
+                                              PTRS_PER_PMD*sizeof(pmd_t),
+                                              PTRS_PER_PMD*sizeof(pmd_t),
+                                              SLAB_PANIC,
+                                              pmd_ctor);
 }
 
 /*
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 6da235522269..5eec5e56d07f 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -166,7 +166,7 @@ early_node_mem(int nodeid, unsigned long start, unsigned long end,
                 return __va(mem);
         ptr = __alloc_bootmem_nopanic(size,
                                 SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
-        if (ptr == 0) {
+        if (ptr == NULL) {
                 printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
                         size, nodeid);
                 return NULL;
@@ -261,7 +261,7 @@ void __init numa_init_array(void)
            We round robin the existing nodes. */
         rr = first_node(node_online_map);
         for (i = 0; i < NR_CPUS; i++) {
-                if (cpu_to_node[i] != NUMA_NO_NODE)
+                if (cpu_to_node(i) != NUMA_NO_NODE)
                         continue;
                 numa_set_node(i, rr);
                 rr = next_node(rr, node_online_map);
@@ -543,7 +543,7 @@ __cpuinit void numa_add_cpu(int cpu)
 void __cpuinit numa_set_node(int cpu, int node)
 {
         cpu_pda(cpu)->nodenumber = node;
-        cpu_to_node[cpu] = node;
+        cpu_to_node(cpu) = node;
 }
 
 unsigned long __init numa_free_all_bootmem(void) 
diff --git a/arch/x86/mm/pageattr_32.c b/arch/x86/mm/pageattr_32.c
index 4241a74d16c8..260073c07600 100644
--- a/arch/x86/mm/pageattr_32.c
+++ b/arch/x86/mm/pageattr_32.c
@@ -70,10 +70,10 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot,
 
 static void cache_flush_page(struct page *p)
 { 
-        unsigned long adr = (unsigned long)page_address(p);
+        void *adr = page_address(p);
         int i;
         for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-                asm volatile("clflush (%0)" :: "r" (adr + i));
+                clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)
diff --git a/arch/x86/mm/pageattr_64.c b/arch/x86/mm/pageattr_64.c
index 10b9809ce821..8a4f65bf956e 100644
--- a/arch/x86/mm/pageattr_64.c
+++ b/arch/x86/mm/pageattr_64.c
@@ -65,7 +65,7 @@ static void cache_flush_page(void *adr)
 {
         int i;
         for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-                asm volatile("clflush (%0)" :: "r" (adr + i));
+                clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)
@@ -148,6 +148,7 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
                         split = split_large_page(address, prot, ref_prot2);
                         if (!split)
                                 return -ENOMEM;
+                        pgprot_val(ref_prot2) &= ~_PAGE_NX;
                         set_pte(kpte, mk_pte(split, ref_prot2));
                         kpte_page = split;
                 }
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index ef1f6cd3ea66..be61a1d845a4 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
+#include <linux/nmi.h>
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
@@ -39,6 +40,8 @@ void show_mem(void)
         for_each_online_pgdat(pgdat) {
                 pgdat_resize_lock(pgdat, &flags);
                 for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+                        if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
+                                touch_nmi_watchdog();
                         page = pgdat_page_nr(pgdat, i);
                         total++;
                         if (PageHighMem(page))
@@ -97,8 +100,7 @@ static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
         }
         pte = pte_offset_kernel(pmd, vaddr);
         if (pgprot_val(flags))
-                /* <pfn,flags> stored as-is, to permit clearing entries */
-                set_pte(pte, pfn_pte(pfn, flags));
+                set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags));
         else
                 pte_clear(&init_mm, vaddr, pte);
 
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index acdf03e19146..56089ccc3949 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -431,9 +431,9 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                         setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 
         for (i = 0; i < NR_CPUS; i++) {
-                if (cpu_to_node[i] == NUMA_NO_NODE)
+                if (cpu_to_node(i) == NUMA_NO_NODE)
                         continue;
-                if (!node_isset(cpu_to_node[i], node_possible_map))
+                if (!node_isset(cpu_to_node(i), node_possible_map))
                         numa_set_node(i, NUMA_NO_NODE);
         }
         numa_init_array();
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 11b7a51566a8..2d0eeac7251f 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -269,7 +269,6 @@ static void nmi_cpu_shutdown(void * dummy)
         apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
         apic_write(APIC_LVTERR, v);
         nmi_restore_registers(msrs);
-        model->shutdown(msrs);
 }
 
  
@@ -278,6 +277,7 @@ static void nmi_shutdown(void)
         nmi_enabled = 0;
         on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
         unregister_die_notifier(&profile_exceptions_nb);
+        model->shutdown(cpu_msrs);
         free_msrs();
 }
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 2d71bbc411d2..f4386990b150 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -289,6 +289,22 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL685c G1"),
                 },
         },
+        {
+                .callback = set_bf_sort,
+                .ident = "HP ProLiant DL385 G2",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+                },
+        },
+        {
+                .callback = set_bf_sort,
+                .ident = "HP ProLiant DL585 G2",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+                },
+        },
 #ifdef __i386__
         {
                 .callback = assign_all_busses,
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index dcd6bb9e0bb3..7a2ba4583939 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -13,7 +13,7 @@ vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
-targets += vdso.so vdso.lds $(vobjs-y) vdso-syms.o
+targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) vdso-syms.o
 
 # The DSO images are built using a special linker script.
 quiet_cmd_syscall = SYSCALL $@
@@ -26,12 +26,19 @@ vdso-flags = -fPIC -shared -Wl,-soname=linux-vdso.so.1 \
                  $(call ld-option, -Wl$(comma)--hash-style=sysv) \
                 -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 SYSCFLAGS_vdso.so = $(vdso-flags)
+SYSCFLAGS_vdso.so.dbg = $(vdso-flags)
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
 
 $(obj)/vdso.so: $(src)/vdso.lds $(vobjs) FORCE
+
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
         $(call if_changed,syscall)
 
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+        $(call if_changed,objcopy)
+
 CFL := $(PROFILING) -mcmodel=small -fPIC -g0 -O2 -fasynchronous-unwind-tables -m64
 
 $(obj)/vclock_gettime.o: KBUILD_CFLAGS = $(CFL)
@@ -47,3 +54,11 @@ $(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
 SYSCFLAGS_vdso-syms.o = -r -d
 $(obj)/vdso-syms.o: $(src)/vdso.lds $(vobjs) FORCE
         $(call if_changed,syscall)
+
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+vdso.so:
+        @mkdir -p $(MODLIB)/vdso
+        $(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S
index b9a60e665d08..667d3245d972 100644
--- a/arch/x86/vdso/vdso.lds.S
+++ b/arch/x86/vdso/vdso.lds.S
@@ -26,13 +26,16 @@ SECTIONS
      is insufficient, ld -shared will barf.  Just increase it here.  */
   . = VDSO_PRELINK + VDSO_TEXT_OFFSET;
 
-  .text           : { *(.text) }                :text
-  .text.ptr       : { *(.text.ptr) }            :text
-  . = VDSO_PRELINK + 0x900;
-  .data           : { *(.data) }                :text
-  .bss            : { *(.bss) }                 :text
+  .text           : { *(.text*) }               :text
+  .rodata         : { *(.rodata*) }             :text
+  .data           : {
+        *(.data*)
+        *(.sdata*)
+        *(.bss*)
+        *(.dynbss*)
+  }                                             :text
 
-  .altinstructions : { *(.altinstructions) }                    :text
+  .altinstructions : { *(.altinstructions) }            :text
   .altinstr_replacement  : { *(.altinstr_replacement) } :text
 
   .note           : { *(.note.*) }              :text :note
@@ -42,7 +45,6 @@ SECTIONS
   .useless        : {
         *(.got.plt) *(.got)
         *(.gnu.linkonce.d.*)
-        *(.dynbss)
         *(.gnu.linkonce.b.*)
   }                                             :text
 }
diff --git a/arch/x86/vdso/vvar.c b/arch/x86/vdso/vvar.c
index 6fc22219a472..1b7e703684f9 100644
--- a/arch/x86/vdso/vvar.c
+++ b/arch/x86/vdso/vvar.c
@@ -8,5 +8,5 @@
 #include <asm/timex.h>
 #include <asm/vgtod.h>
 
-#define VEXTERN(x) typeof (__ ## x) *vdso_ ## x = (void *)VMAGIC;
+#define VEXTERN(x) typeof (__ ## x) *const vdso_ ## x = (void *)VMAGIC;
 #include "vextern.h"
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 493a083f6886..94c39aaf695f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -25,7 +25,6 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
-#include <linux/smp.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/physdev.h>
@@ -52,11 +51,25 @@
 
 EXPORT_SYMBOL_GPL(hypercall_page);
 
-DEFINE_PER_CPU(enum paravirt_lazy_mode, xen_lazy_mode);
-
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
-DEFINE_PER_CPU(unsigned long, xen_cr3);
+
+/*
+ * Note about cr3 (pagetable base) values:
+ *
+ * xen_cr3 contains the current logical cr3 value; it contains the
+ * last set cr3.  This may not be the current effective cr3, because
+ * its update may be being lazily deferred.  However, a vcpu looking
+ * at its own cr3 can use this value knowing that it everything will
+ * be self-consistent.
+ *
+ * xen_current_cr3 contains the actual vcpu cr3; it is set once the
+ * hypercall to set the vcpu cr3 is complete (so it may be a little
+ * out of date, but it will never be set early).  If one vcpu is
+ * looking at another vcpu's cr3 value, it should use this variable.
+ */
+DEFINE_PER_CPU(unsigned long, xen_cr3);  /* cr3 stored as physaddr */
+DEFINE_PER_CPU(unsigned long, xen_current_cr3);  /* actual vcpu cr3 */
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -100,7 +113,7 @@ static void __init xen_vcpu_setup(int cpu)
         info.mfn = virt_to_mfn(vcpup);
         info.offset = offset_in_page(vcpup);
 
-        printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %x, offset %d\n",
+        printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
                cpu, vcpup, info.mfn, info.offset);
 
         /* Check to see if the hypervisor will put the vcpu_info
@@ -124,7 +137,7 @@ static void __init xen_vcpu_setup(int cpu)
 static void __init xen_banner(void)
 {
         printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
-               paravirt_ops.name);
+               pv_info.name);
         printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
 }
 
@@ -249,29 +262,10 @@ static void xen_halt(void)
                 xen_safe_halt();
 }
 
-static void xen_set_lazy_mode(enum paravirt_lazy_mode mode)
+static void xen_leave_lazy(void)
 {
-        BUG_ON(preemptible());
-
-        switch (mode) {
-        case PARAVIRT_LAZY_NONE:
-                BUG_ON(x86_read_percpu(xen_lazy_mode) == PARAVIRT_LAZY_NONE);
-                break;
-
-        case PARAVIRT_LAZY_MMU:
-        case PARAVIRT_LAZY_CPU:
-                BUG_ON(x86_read_percpu(xen_lazy_mode) != PARAVIRT_LAZY_NONE);
-                break;
-
-        case PARAVIRT_LAZY_FLUSH:
-                /* flush if necessary, but don't change state */
-                if (x86_read_percpu(xen_lazy_mode) != PARAVIRT_LAZY_NONE)
-                        xen_mc_flush();
-                return;
-        }
-
+        paravirt_leave_lazy(paravirt_get_lazy_mode());
         xen_mc_flush();
-        x86_write_percpu(xen_lazy_mode, mode);
 }
 
 static unsigned long xen_store_tr(void)
@@ -358,7 +352,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
          * loaded properly.  This will go away as soon as Xen has been
          * modified to not save/restore %gs for normal hypercalls.
          */
-        if (xen_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
                 loadsegment(gs, 0);
 }
 
@@ -632,32 +626,36 @@ static unsigned long xen_read_cr3(void)
         return x86_read_percpu(xen_cr3);
 }
 
+static void set_current_cr3(void *v)
+{
+        x86_write_percpu(xen_current_cr3, (unsigned long)v);
+}
+
 static void xen_write_cr3(unsigned long cr3)
 {
+        struct mmuext_op *op;
+        struct multicall_space mcs;
+        unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
+
         BUG_ON(preemptible());
 
-        if (cr3 == x86_read_percpu(xen_cr3)) {
-                /* just a simple tlb flush */
-                xen_flush_tlb();
-                return;
-        }
+        mcs = xen_mc_entry(sizeof(*op));  /* disables interrupts */
 
+        /* Update while interrupts are disabled, so its atomic with
+           respect to ipis */
         x86_write_percpu(xen_cr3, cr3);
 
+        op = mcs.args;
+        op->cmd = MMUEXT_NEW_BASEPTR;
+        op->arg1.mfn = mfn;
 
-        {
-                struct mmuext_op *op;
-                struct multicall_space mcs = xen_mc_entry(sizeof(*op));
-                unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
-
-                op = mcs.args;
-                op->cmd = MMUEXT_NEW_BASEPTR;
-                op->arg1.mfn = mfn;
+        MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-                MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+        /* Update xen_update_cr3 once the batch has actually
+           been submitted. */
+        xen_mc_callback(set_current_cr3, (void *)cr3);
 
-                xen_mc_issue(PARAVIRT_LAZY_CPU);
-        }
+        xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
 
 /* Early in boot, while setting up the initial pagetable, assume
@@ -668,6 +666,15 @@ static __init void xen_alloc_pt_init(struct mm_struct *mm, u32 pfn)
         make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
 }
 
+static void pin_pagetable_pfn(unsigned level, unsigned long pfn)
+{
+        struct mmuext_op op;
+        op.cmd = level;
+        op.arg1.mfn = pfn_to_mfn(pfn);
+        if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+                BUG();
+}
+
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
 static void xen_alloc_pt(struct mm_struct *mm, u32 pfn)
@@ -677,9 +684,10 @@ static void xen_alloc_pt(struct mm_struct *mm, u32 pfn)
         if (PagePinned(virt_to_page(mm->pgd))) {
                 SetPagePinned(page);
 
-                if (!PageHighMem(page))
+                if (!PageHighMem(page)) {
                         make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
-                else
+                        pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+                } else
                         /* make sure there are no stray mappings of
                            this page */
                         kmap_flush_unused();
@@ -692,8 +700,10 @@ static void xen_release_pt(u32 pfn)
         struct page *page = pfn_to_page(pfn);
 
         if (PagePinned(page)) {
-                if (!PageHighMem(page))
+                if (!PageHighMem(page)) {
+                        pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
                         make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+                }
         }
 }
 
@@ -738,7 +748,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
         pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
 
         /* special set_pte for pagetable initialization */
-        paravirt_ops.set_pte = xen_set_pte_init;
+        pv_mmu_ops.set_pte = xen_set_pte_init;
 
         init_mm.pgd = base;
         /*
@@ -785,8 +795,8 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 {
         /* This will work as long as patching hasn't happened yet
            (which it hasn't) */
-        paravirt_ops.alloc_pt = xen_alloc_pt;
-        paravirt_ops.set_pte = xen_set_pte;
+        pv_mmu_ops.alloc_pt = xen_alloc_pt;
+        pv_mmu_ops.set_pte = xen_set_pte;
 
         if (!xen_feature(XENFEAT_auto_translated_physmap)) {
                 /*
@@ -808,15 +818,15 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
         /* Actually pin the pagetable down, but we can't set PG_pinned
            yet because the page structures don't exist yet. */
         {
-                struct mmuext_op op;
+                unsigned level;
+
 #ifdef CONFIG_X86_PAE
-                op.cmd = MMUEXT_PIN_L3_TABLE;
+                level = MMUEXT_PIN_L3_TABLE;
 #else
-                op.cmd = MMUEXT_PIN_L3_TABLE;
+                level = MMUEXT_PIN_L2_TABLE;
 #endif
-                op.arg1.mfn = pfn_to_mfn(PFN_DOWN(__pa(base)));
-                if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-                        BUG();
+
+                pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
         }
 }
 
@@ -833,12 +843,12 @@ void __init xen_setup_vcpu_info_placement(void)
         if (have_vcpu_info_placement) {
                 printk(KERN_INFO "Xen: using vcpu_info placement\n");
 
-                paravirt_ops.save_fl = xen_save_fl_direct;
-                paravirt_ops.restore_fl = xen_restore_fl_direct;
-                paravirt_ops.irq_disable = xen_irq_disable_direct;
-                paravirt_ops.irq_enable = xen_irq_enable_direct;
-                paravirt_ops.read_cr2 = xen_read_cr2_direct;
-                paravirt_ops.iret = xen_iret_direct;
+                pv_irq_ops.save_fl = xen_save_fl_direct;
+                pv_irq_ops.restore_fl = xen_restore_fl_direct;
+                pv_irq_ops.irq_disable = xen_irq_disable_direct;
+                pv_irq_ops.irq_enable = xen_irq_enable_direct;
+                pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
+                pv_cpu_ops.iret = xen_iret_direct;
         }
 }
 
@@ -850,8 +860,8 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 
         start = end = reloc = NULL;
 
-#define SITE(x)                                                         \
-        case PARAVIRT_PATCH(x):                                         \
+#define SITE(op, x)                                                     \
+        case PARAVIRT_PATCH(op.x):                                      \
         if (have_vcpu_info_placement) {                                 \
                 start = (char *)xen_##x##_direct;                       \
                 end = xen_##x##_direct_end;                             \
@@ -860,10 +870,10 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
         goto patch_site
 
         switch (type) {
-                SITE(irq_enable);
-                SITE(irq_disable);
-                SITE(save_fl);
-                SITE(restore_fl);
+                SITE(pv_irq_ops, irq_enable);
+                SITE(pv_irq_ops, irq_disable);
+                SITE(pv_irq_ops, save_fl);
+                SITE(pv_irq_ops, restore_fl);
 #undef SITE
 
         patch_site:
@@ -895,26 +905,32 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
         return ret;
 }
 
-static const struct paravirt_ops xen_paravirt_ops __initdata = {
+static const struct pv_info xen_info __initdata = {
         .paravirt_enabled = 1,
         .shared_kernel_pmd = 0,
 
         .name = "Xen",
-        .banner = xen_banner,
+};
 
+static const struct pv_init_ops xen_init_ops __initdata = {
         .patch = xen_patch,
 
+        .banner = xen_banner,
         .memory_setup = xen_memory_setup,
         .arch_setup = xen_arch_setup,
-        .init_IRQ = xen_init_IRQ,
         .post_allocator_init = xen_mark_init_mm_pinned,
+};
 
+static const struct pv_time_ops xen_time_ops __initdata = {
         .time_init = xen_time_init,
+
         .set_wallclock = xen_set_wallclock,
         .get_wallclock = xen_get_wallclock,
         .get_cpu_khz = xen_cpu_khz,
         .sched_clock = xen_sched_clock,
+};
 
+static const struct pv_cpu_ops xen_cpu_ops __initdata = {
         .cpuid = xen_cpuid,
 
         .set_debugreg = xen_set_debugreg,
@@ -925,22 +941,10 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
         .read_cr0 = native_read_cr0,
         .write_cr0 = native_write_cr0,
 
-        .read_cr2 = xen_read_cr2,
-        .write_cr2 = xen_write_cr2,
-
-        .read_cr3 = xen_read_cr3,
-        .write_cr3 = xen_write_cr3,
-
         .read_cr4 = native_read_cr4,
         .read_cr4_safe = native_read_cr4_safe,
         .write_cr4 = xen_write_cr4,
 
-        .save_fl = xen_save_fl,
-        .restore_fl = xen_restore_fl,
-        .irq_disable = xen_irq_disable,
-        .irq_enable = xen_irq_enable,
-        .safe_halt = xen_safe_halt,
-        .halt = xen_halt,
         .wbinvd = native_wbinvd,
 
         .read_msr = native_read_msr_safe,
@@ -969,6 +973,23 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
         .set_iopl_mask = xen_set_iopl_mask,
         .io_delay = xen_io_delay,
 
+        .lazy_mode = {
+                .enter = paravirt_enter_lazy_cpu,
+                .leave = xen_leave_lazy,
+        },
+};
+
+static const struct pv_irq_ops xen_irq_ops __initdata = {
+        .init_IRQ = xen_init_IRQ,
+        .save_fl = xen_save_fl,
+        .restore_fl = xen_restore_fl,
+        .irq_disable = xen_irq_disable,
+        .irq_enable = xen_irq_enable,
+        .safe_halt = xen_safe_halt,
+        .halt = xen_halt,
+};
+
+static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
         .apic_write = xen_apic_write,
         .apic_write_atomic = xen_apic_write,
@@ -977,6 +998,17 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
         .setup_secondary_clock = paravirt_nop,
         .startup_ipi_hook = paravirt_nop,
 #endif
+};
+
+static const struct pv_mmu_ops xen_mmu_ops __initdata = {
+        .pagetable_setup_start = xen_pagetable_setup_start,
+        .pagetable_setup_done = xen_pagetable_setup_done,
+
+        .read_cr2 = xen_read_cr2,
+        .write_cr2 = xen_write_cr2,
+
+        .read_cr3 = xen_read_cr3,
+        .write_cr3 = xen_write_cr3,
 
         .flush_tlb_user = xen_flush_tlb,
         .flush_tlb_kernel = xen_flush_tlb,
@@ -986,9 +1018,6 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
         .pte_update = paravirt_nop,
         .pte_update_defer = paravirt_nop,
 
-        .pagetable_setup_start = xen_pagetable_setup_start,
-        .pagetable_setup_done = xen_pagetable_setup_done,
-
         .alloc_pt = xen_alloc_pt_init,
         .release_pt = xen_release_pt,
         .alloc_pd = paravirt_nop,
@@ -1024,7 +1053,10 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
         .dup_mmap = xen_dup_mmap,
         .exit_mmap = xen_exit_mmap,
 
-        .set_lazy_mode = xen_set_lazy_mode,
+        .lazy_mode = {
+                .enter = paravirt_enter_lazy_mmu,
+                .leave = xen_leave_lazy,
+        },
 };
 
 #ifdef CONFIG_SMP
@@ -1080,6 +1112,17 @@ static const struct machine_ops __initdata xen_machine_ops = {
 };
 
 
+static void __init xen_reserve_top(void)
+{
+        unsigned long top = HYPERVISOR_VIRT_START;
+        struct xen_platform_parameters pp;
+
+        if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
+                top = pp.virt_start;
+
+        reserve_top_address(-top + 2 * PAGE_SIZE);
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
@@ -1091,7 +1134,14 @@ asmlinkage void __init xen_start_kernel(void)
         BUG_ON(memcmp(xen_start_info->magic, "xen-3.0", 7) != 0);
 
         /* Install Xen paravirt ops */
-        paravirt_ops = xen_paravirt_ops;
+        pv_info = xen_info;
+        pv_init_ops = xen_init_ops;
+        pv_time_ops = xen_time_ops;
+        pv_cpu_ops = xen_cpu_ops;
+        pv_irq_ops = xen_irq_ops;
+        pv_apic_ops = xen_apic_ops;
+        pv_mmu_ops = xen_mmu_ops;
+
         machine_ops = xen_machine_ops;
 
 #ifdef CONFIG_SMP
@@ -1113,6 +1163,7 @@ asmlinkage void __init xen_start_kernel(void)
         /* keep using Xen gdt for now; no urgent need to change it */
 
         x86_write_percpu(xen_cr3, __pa(pgd));
+        x86_write_percpu(xen_current_cr3, __pa(pgd));
 
 #ifdef CONFIG_SMP
         /* Don't do the full vcpu_info placement stuff until we have a
@@ -1124,12 +1175,12 @@ asmlinkage void __init xen_start_kernel(void)
         xen_setup_vcpu_info_placement();
 #endif
 
-        paravirt_ops.kernel_rpl = 1;
+        pv_info.kernel_rpl = 1;
         if (xen_feature(XENFEAT_supervisor_mode_kernel))
-                paravirt_ops.kernel_rpl = 0;
+                pv_info.kernel_rpl = 0;
 
         /* set the limit of our address space */
-        reserve_top_address(-HYPERVISOR_VIRT_START + 2 * PAGE_SIZE);
+        xen_reserve_top();
 
         /* set up basic CPUID stuff */
         cpu_detect(&new_cpu_data);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 874db0cd1d2a..b2e32f9d0071 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -41,7 +41,6 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/bug.h>
-#include <linux/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -155,7 +154,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
                     pte_t *ptep, pte_t pteval)
 {
         if (mm == current->mm || mm == &init_mm) {
-                if (xen_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+                if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
                         struct multicall_space mcs;
                         mcs = xen_mc_entry(0);
 
@@ -304,7 +303,12 @@ pgd_t xen_make_pgd(unsigned long pgd)
 }
 #endif  /* CONFIG_X86_PAE */
 
-
+enum pt_level {
+        PT_PGD,
+        PT_PUD,
+        PT_PMD,
+        PT_PTE
+};
 
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
@@ -316,7 +320,7 @@ pgd_t xen_make_pgd(unsigned long pgd)
   FIXADDR_TOP.  But the important bit is that we don't pin beyond
   there, because then we start getting into Xen's ptes.
 */
-static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
+static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, enum pt_level),
                     unsigned long limit)
 {
         pgd_t *pgd = pgd_base;
@@ -341,7 +345,7 @@ static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
                 pud = pud_offset(pgd, 0);
 
                 if (PTRS_PER_PUD > 1) /* not folded */
-                        flush |= (*func)(virt_to_page(pud), 0);
+                        flush |= (*func)(virt_to_page(pud), PT_PUD);
 
                 for (; addr != pud_limit; pud++, addr = pud_next) {
                         pmd_t *pmd;
@@ -360,7 +364,7 @@ static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
                         pmd = pmd_offset(pud, 0);
 
                         if (PTRS_PER_PMD > 1) /* not folded */
-                                flush |= (*func)(virt_to_page(pmd), 0);
+                                flush |= (*func)(virt_to_page(pmd), PT_PMD);
 
                         for (; addr != pmd_limit; pmd++) {
                                 addr += (PAGE_SIZE * PTRS_PER_PTE);
@@ -372,17 +376,47 @@ static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
                                 if (pmd_none(*pmd))
                                         continue;
 
-                                flush |= (*func)(pmd_page(*pmd), 0);
+                                flush |= (*func)(pmd_page(*pmd), PT_PTE);
                         }
                 }
         }
 
-        flush |= (*func)(virt_to_page(pgd_base), UVMF_TLB_FLUSH);
+        flush |= (*func)(virt_to_page(pgd_base), PT_PGD);
 
         return flush;
 }
 
-static int pin_page(struct page *page, unsigned flags)
+static spinlock_t *lock_pte(struct page *page)
+{
+        spinlock_t *ptl = NULL;
+
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+        ptl = __pte_lockptr(page);
+        spin_lock(ptl);
+#endif
+
+        return ptl;
+}
+
+static void do_unlock(void *v)
+{
+        spinlock_t *ptl = v;
+        spin_unlock(ptl);
+}
+
+static void xen_do_pin(unsigned level, unsigned long pfn)
+{
+        struct mmuext_op *op;
+        struct multicall_space mcs;
+
+        mcs = __xen_mc_entry(sizeof(*op));
+        op = mcs.args;
+        op->cmd = level;
+        op->arg1.mfn = pfn_to_mfn(pfn);
+        MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+}
+
+static int pin_page(struct page *page, enum pt_level level)
 {
         unsigned pgfl = test_and_set_bit(PG_pinned, &page->flags);
         int flush;
@@ -397,12 +431,26 @@ static int pin_page(struct page *page, unsigned flags)
                 void *pt = lowmem_page_address(page);
                 unsigned long pfn = page_to_pfn(page);
                 struct multicall_space mcs = __xen_mc_entry(0);
+                spinlock_t *ptl;
 
                 flush = 0;
 
+                ptl = NULL;
+                if (level == PT_PTE)
+                        ptl = lock_pte(page);
+
                 MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
                                         pfn_pte(pfn, PAGE_KERNEL_RO),
-                                        flags);
+                                        level == PT_PGD ? UVMF_TLB_FLUSH : 0);
+
+                if (level == PT_PTE)
+                        xen_do_pin(MMUEXT_PIN_L1_TABLE, pfn);
+
+                if (ptl) {
+                        /* Queue a deferred unlock for when this batch
+                           is completed. */
+                        xen_mc_callback(do_unlock, ptl);
+                }
         }
 
         return flush;
@@ -413,8 +461,7 @@ static int pin_page(struct page *page, unsigned flags)
    read-only, and can be pinned. */
 void xen_pgd_pin(pgd_t *pgd)
 {
-        struct multicall_space mcs;
-        struct mmuext_op *op;
+        unsigned level;
 
         xen_mc_batch();
 
@@ -425,16 +472,13 @@ void xen_pgd_pin(pgd_t *pgd)
                 xen_mc_batch();
         }
 
-        mcs = __xen_mc_entry(sizeof(*op));
-        op = mcs.args;
-
 #ifdef CONFIG_X86_PAE
-        op->cmd = MMUEXT_PIN_L3_TABLE;
+        level = MMUEXT_PIN_L3_TABLE;
 #else
-        op->cmd = MMUEXT_PIN_L2_TABLE;
+        level = MMUEXT_PIN_L2_TABLE;
 #endif
-        op->arg1.mfn = pfn_to_mfn(PFN_DOWN(__pa(pgd)));
-        MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+        xen_do_pin(level, PFN_DOWN(__pa(pgd)));
 
         xen_mc_issue(0);
 }
@@ -442,7 +486,7 @@ void xen_pgd_pin(pgd_t *pgd)
 /* The init_mm pagetable is really pinned as soon as its created, but
    that's before we have page structures to store the bits.  So do all
    the book-keeping now. */
-static __init int mark_pinned(struct page *page, unsigned flags)
+static __init int mark_pinned(struct page *page, enum pt_level level)
 {
         SetPagePinned(page);
         return 0;
@@ -453,18 +497,32 @@ void __init xen_mark_init_mm_pinned(void)
         pgd_walk(init_mm.pgd, mark_pinned, FIXADDR_TOP);
 }
 
-static int unpin_page(struct page *page, unsigned flags)
+static int unpin_page(struct page *page, enum pt_level level)
 {
         unsigned pgfl = test_and_clear_bit(PG_pinned, &page->flags);
 
         if (pgfl && !PageHighMem(page)) {
                 void *pt = lowmem_page_address(page);
                 unsigned long pfn = page_to_pfn(page);
-                struct multicall_space mcs = __xen_mc_entry(0);
+                spinlock_t *ptl = NULL;
+                struct multicall_space mcs;
+
+                if (level == PT_PTE) {
+                        ptl = lock_pte(page);
+
+                        xen_do_pin(MMUEXT_UNPIN_TABLE, pfn);
+                }
+
+                mcs = __xen_mc_entry(0);
 
                 MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
                                         pfn_pte(pfn, PAGE_KERNEL),
-                                        flags);
+                                        level == PT_PGD ? UVMF_TLB_FLUSH : 0);
+
+                if (ptl) {
+                        /* unlock when batch completed */
+                        xen_mc_callback(do_unlock, ptl);
+                }
         }
 
         return 0;               /* never need to flush on unpin */
@@ -473,18 +531,9 @@ static int unpin_page(struct page *page, unsigned flags)
 /* Release a pagetables pages back as normal RW */
 static void xen_pgd_unpin(pgd_t *pgd)
 {
-        struct mmuext_op *op;
-        struct multicall_space mcs;
-
         xen_mc_batch();
 
-        mcs = __xen_mc_entry(sizeof(*op));
-
-        op = mcs.args;
-        op->cmd = MMUEXT_UNPIN_TABLE;
-        op->arg1.mfn = pfn_to_mfn(PFN_DOWN(__pa(pgd)));
-
-        MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+        xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
         pgd_walk(pgd, unpin_page, TASK_SIZE);
 
@@ -515,20 +564,43 @@ static void drop_other_mm_ref(void *info)
 
         if (__get_cpu_var(cpu_tlbstate).active_mm == mm)
                 leave_mm(smp_processor_id());
+
+        /* If this cpu still has a stale cr3 reference, then make sure
+           it has been flushed. */
+        if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) {
+                load_cr3(swapper_pg_dir);
+                arch_flush_lazy_cpu_mode();
+        }
 }
 
 static void drop_mm_ref(struct mm_struct *mm)
 {
+        cpumask_t mask;
+        unsigned cpu;
+
         if (current->active_mm == mm) {
                 if (current->mm == mm)
                         load_cr3(swapper_pg_dir);
                 else
                         leave_mm(smp_processor_id());
+                arch_flush_lazy_cpu_mode();
         }
 
-        if (!cpus_empty(mm->cpu_vm_mask))
-                xen_smp_call_function_mask(mm->cpu_vm_mask, drop_other_mm_ref,
-                                           mm, 1);
+        /* Get the "official" set of cpus referring to our pagetable. */
+        mask = mm->cpu_vm_mask;
+
+        /* It's possible that a vcpu may have a stale reference to our
+           cr3, because its in lazy mode, and it hasn't yet flushed
+           its set of pending hypercalls yet.  In this case, we can
+           look at its actual current cr3 value, and force it to flush
+           if needed. */
+        for_each_online_cpu(cpu) {
+                if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
+                        cpu_set(cpu, mask);
+        }
+
+        if (!cpus_empty(mask))
+                xen_smp_call_function_mask(mask, drop_other_mm_ref, mm, 1);
 }
 #else
 static void drop_mm_ref(struct mm_struct *mm)
@@ -563,5 +635,6 @@ void xen_exit_mmap(struct mm_struct *mm)
         /* pgd may not be pinned in the error exit path of execve */
         if (PagePinned(virt_to_page(mm->pgd)))
                 xen_pgd_unpin(mm->pgd);
+
         spin_unlock(&mm->page_table_lock);
 }
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index c837e8e463db..5e6f36f6d876 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -26,13 +26,22 @@
 
 #include "multicalls.h"
 
+#define MC_DEBUG        1
+
 #define MC_BATCH        32
 #define MC_ARGS         (MC_BATCH * 16 / sizeof(u64))
 
 struct mc_buffer {
         struct multicall_entry entries[MC_BATCH];
+#if MC_DEBUG
+        struct multicall_entry debug[MC_BATCH];
+#endif
         u64 args[MC_ARGS];
-        unsigned mcidx, argidx;
+        struct callback {
+                void (*fn)(void *);
+                void *data;
+        } callbacks[MC_BATCH];
+        unsigned mcidx, argidx, cbidx;
 };
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
@@ -43,6 +52,7 @@ void xen_mc_flush(void)
         struct mc_buffer *b = &__get_cpu_var(mc_buffer);
         int ret = 0;
         unsigned long flags;
+        int i;
 
         BUG_ON(preemptible());
 
@@ -51,13 +61,31 @@ void xen_mc_flush(void)
         local_irq_save(flags);
 
         if (b->mcidx) {
-                int i;
+#if MC_DEBUG
+                memcpy(b->debug, b->entries,
+                       b->mcidx * sizeof(struct multicall_entry));
+#endif
 
                 if (HYPERVISOR_multicall(b->entries, b->mcidx) != 0)
                         BUG();
                 for (i = 0; i < b->mcidx; i++)
                         if (b->entries[i].result < 0)
                                 ret++;
+
+#if MC_DEBUG
+                if (ret) {
+                        printk(KERN_ERR "%d multicall(s) failed: cpu %d\n",
+                               ret, smp_processor_id());
+                        for(i = 0; i < b->mcidx; i++) {
+                                printk("  call %2d/%d: op=%lu arg=[%lx] result=%ld\n",
+                                       i+1, b->mcidx,
+                                       b->debug[i].op,
+                                       b->debug[i].args[0],
+                                       b->entries[i].result);
+                        }
+                }
+#endif
+
                 b->mcidx = 0;
                 b->argidx = 0;
         } else
@@ -65,6 +93,13 @@ void xen_mc_flush(void)
 
         local_irq_restore(flags);
 
+        for(i = 0; i < b->cbidx; i++) {
+                struct callback *cb = &b->callbacks[i];
+
+                (*cb->fn)(cb->data);
+        }
+        b->cbidx = 0;
+
         BUG_ON(ret);
 }
 
@@ -88,3 +123,16 @@ struct multicall_space __xen_mc_entry(size_t args)
 
         return ret;
 }
+
+void xen_mc_callback(void (*fn)(void *), void *data)
+{
+        struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+        struct callback *cb;
+
+        if (b->cbidx == MC_BATCH)
+                xen_mc_flush();
+
+        cb = &b->callbacks[b->cbidx++];
+        cb->fn = fn;
+        cb->data = data;
+}
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index e6f7530b156c..8bae996d99a3 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -35,11 +35,14 @@ void xen_mc_flush(void);
 /* Issue a multicall if we're not in a lazy mode */
 static inline void xen_mc_issue(unsigned mode)
 {
-        if ((xen_get_lazy_mode() & mode) == 0)
+        if ((paravirt_get_lazy_mode() & mode) == 0)
                 xen_mc_flush();
 
         /* restore flags saved in xen_mc_batch */
         local_irq_restore(x86_read_percpu(xen_mc_irq_flags));
 }
 
+/* Set up a callback to be called when the current batch is flushed */
+void xen_mc_callback(void (*fn)(void *), void *data);
+
 #endif /* _XEN_MULTICALLS_H */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4fa33c27ccb6..c1b131bcdcbe 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -356,6 +356,7 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
          */
         irq_enter();
         (*func)(info);
+        __get_cpu_var(irq_stat).irq_call_count++;
         irq_exit();
 
         if (wait) {
@@ -370,7 +371,8 @@ int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
                                void *info, int wait)
 {
         struct call_data_struct data;
-        int cpus;
+        int cpus, cpu;
+        bool yield;
 
         /* Holding any lock stops cpus from going down. */
         spin_lock(&call_lock);
@@ -399,9 +401,14 @@ int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
         /* Send a message to other CPUs and wait for them to respond */
         xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
 
-        /* Make sure other vcpus get a chance to run.
-           XXX too severe?  Maybe we should check the other CPU's states? */
-        HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+        /* Make sure other vcpus get a chance to run if they need to. */
+        yield = false;
+        for_each_cpu_mask(cpu, mask)
+                if (xen_vcpu_stolen(cpu))
+                        yield = true;
+
+        if (yield)
+                HYPERVISOR_sched_op(SCHEDOP_yield, 0);
 
         /* Wait for response */
         while (atomic_read(&data.started) != cpus ||
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index dfd6db69ead5..d083ff5ef088 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -105,6 +105,12 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
         } while (get64(&state->state_entry_time) != state_time);
 }
 
+/* return true when a vcpu could run but has no real cpu to run on */
+bool xen_vcpu_stolen(int vcpu)
+{
+        return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
+}
+
 static void setup_runstate_info(int cpu)
 {
         struct vcpu_register_runstate_memory_area area;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b9aaea45f07f..b02a909bfd4c 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -11,6 +11,7 @@ void xen_copy_trap_info(struct trap_info *traps);
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DECLARE_PER_CPU(unsigned long, xen_cr3);
+DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
 extern struct start_info *xen_start_info;
 extern struct shared_info *HYPERVISOR_shared_info;
@@ -27,14 +28,9 @@ unsigned long xen_get_wallclock(void);
 int xen_set_wallclock(unsigned long time);
 unsigned long long xen_sched_clock(void);
 
-void xen_mark_init_mm_pinned(void);
-
-DECLARE_PER_CPU(enum paravirt_lazy_mode, xen_lazy_mode);
+bool xen_vcpu_stolen(int vcpu);
 
-static inline unsigned xen_get_lazy_mode(void)
-{
-        return x86_read_percpu(xen_lazy_mode);
-}
+void xen_mark_init_mm_pinned(void);
 
 void __init xen_fill_possible_map(void);
 
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index d681be88ae5d..43fafe9e9c08 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -175,14 +175,12 @@ config MK8
 config MPSC
        bool "Intel P4 / older Netburst based Xeon"
        help
-          Optimize for Intel Pentium 4 and older Nocona/Dempsey Xeon CPUs
-          with Intel Extended Memory 64 Technology(EM64T). For details see
-          <http://www.intel.com/technology/64bitextensions/>.
+          Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
+          Xeon CPUs with Intel 64bit which is compatible with x86-64.
           Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
           Netburst core and shouldn't use this option. You can distinguish them
           using the cpu family field
-          in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one
-          (this rule only applies to systems that support EM64T)
+          in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
 
 config MCORE2
         bool "Intel Core2 / newer Xeon"
@@ -190,8 +188,7 @@ config MCORE2
           Optimize for Intel Core2 and newer Xeons (51xx)
           You can distinguish the newer Xeons from the older ones using
           the cpu family field in /proc/cpuinfo. 15 is an older Xeon
-          (use CONFIG_MPSC then), 6 is a newer one. This rule only
-          applies to CPUs that support EM64T.
+          (use CONFIG_MPSC then), 6 is a newer one.
 
 config GENERIC_CPU
         bool "Generic-x86-64"
@@ -476,8 +473,9 @@ config HPET_TIMER
           <http://www.intel.com/hardwaredesign/hpetspec.htm>.
 
 config HPET_EMULATE_RTC
-        bool "Provide RTC interrupt"
+        bool
         depends on HPET_TIMER && RTC=y
+        default y
 
 # Mark as embedded because too many people got it wrong.
 # The code disables itself when not needed.
diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile
index 9daa32d1d2a1..03e1ede27b85 100644
--- a/arch/x86_64/Makefile
+++ b/arch/x86_64/Makefile
@@ -110,9 +110,15 @@ bzdisk: vmlinux
 fdimage fdimage144 fdimage288 isoimage: vmlinux
         $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
 
-install:
+install: vdso_install
         $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@ 
 
+vdso_install:
+ifeq ($(CONFIG_IA32_EMULATION),y)
+        $(Q)$(MAKE) $(build)=arch/x86/ia32 $@
+endif
+        $(Q)$(MAKE) $(build)=arch/x86/vdso $@
+
 archclean:
         $(Q)rm -rf $(objtree)/arch/x86_64/boot
         $(Q)$(MAKE) $(clean)=$(boot)
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 9e3f3cc85d0d..3935469e3662 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -1322,8 +1322,8 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
                   struct scatterlist *sglist)
 {
         struct bio_vec *bvec, *bvprv;
-        struct scatterlist *next_sg, *sg;
         struct req_iterator iter;
+        struct scatterlist *sg;
         int nsegs, cluster;
 
         nsegs = 0;
@@ -1333,7 +1333,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
          * for each bio in rq
          */
         bvprv = NULL;
-        sg = next_sg = &sglist[0];
+        sg = NULL;
         rq_for_each_segment(bvec, rq, iter) {
                 int nbytes = bvec->bv_len;
 
@@ -1349,8 +1349,10 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
                         sg->length += nbytes;
                 } else {
 new_segment:
-                        sg = next_sg;
-                        next_sg = sg_next(sg);
+                        if (!sg)
+                                sg = sglist;
+                        else
+                                sg = sg_next(sg);
 
                         memset(sg, 0, sizeof(*sg));
                         sg->page = bvec->bv_page;
diff --git a/drivers/char/agp/efficeon-agp.c b/drivers/char/agp/efficeon-agp.c
index d78cd09186aa..cac0009cebc1 100644
--- a/drivers/char/agp/efficeon-agp.c
+++ b/drivers/char/agp/efficeon-agp.c
@@ -221,7 +221,7 @@ static int efficeon_create_gatt_table(struct agp_bridge_data *bridge)
                 SetPageReserved(virt_to_page((char *)page));
 
                 for (offset = 0; offset < PAGE_SIZE; offset += clflush_chunk)
-                        asm volatile("clflush %0" : : "m" (*(char *)(page+offset)));
+                        clflush((char *)page+offset);
 
                 efficeon_private.l1_table[index] = page;
 
@@ -268,15 +268,16 @@ static int efficeon_insert_memory(struct agp_memory * mem, off_t pg_start, int t
                 *page = insert;
 
                 /* clflush is slow, so don't clflush until we have to */
-                if ( last_page &&
-                     ((unsigned long)page^(unsigned long)last_page) & clflush_mask )
-                    asm volatile("clflush %0" : : "m" (*last_page));
+                if (last_page &&
+                    (((unsigned long)page^(unsigned long)last_page) &
+                     clflush_mask))
+                        clflush(last_page);
 
                 last_page = page;
         }
 
         if ( last_page )
-                asm volatile("clflush %0" : : "m" (*last_page));
+                clflush(last_page);
 
         agp_bridge->driver->tlb_flush(mem);
         return 0;
diff --git a/drivers/char/hvc_lguest.c b/drivers/char/hvc_lguest.c
index 3d6bd0baa56d..efccb2155830 100644
--- a/drivers/char/hvc_lguest.c
+++ b/drivers/char/hvc_lguest.c
@@ -115,7 +115,7 @@ static struct hv_ops lguest_cons = {
  * (0), and the struct hv_ops containing the put_chars() function. */
 static int __init cons_init(void)
 {
-        if (strcmp(paravirt_ops.name, "lguest") != 0)
+        if (strcmp(pv_info.name, "lguest") != 0)
                 return 0;
 
         return hvc_instantiate(0, 0, &lguest_cons);
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 4a315f08a567..a0788c12b392 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -248,8 +248,8 @@ static void unmap_switcher(void)
 }
 
 /*H:130 Our Guest is usually so well behaved; it never tries to do things it
- * isn't allowed to.  Unfortunately, "struct paravirt_ops" isn't quite
- * complete, because it doesn't contain replacements for the Intel I/O
+ * isn't allowed to.  Unfortunately, Linux's paravirtual infrastructure isn't
+ * quite complete, because it doesn't contain replacements for the Intel I/O
  * instructions.  As a result, the Guest sometimes fumbles across one during
  * the boot process as it probes for various things which are usually attached
  * to a PC.
@@ -694,7 +694,7 @@ static int __init init(void)
 
         /* Lguest can't run under Xen, VMI or itself.  It does Tricky Stuff. */
         if (paravirt_enabled()) {
-                printk("lguest is afraid of %s\n", paravirt_ops.name);
+                printk("lguest is afraid of %s\n", pv_info.name);
                 return -EPERM;
         }
 
diff --git a/drivers/lguest/lguest.c b/drivers/lguest/lguest.c
index 4a579c840301..3ba337dde857 100644
--- a/drivers/lguest/lguest.c
+++ b/drivers/lguest/lguest.c
@@ -23,7 +23,7 @@
  *
  * So how does the kernel know it's a Guest?  The Guest starts at a special
  * entry point marked with a magic string, which sets up a few things then
- * calls here.  We replace the native functions in "struct paravirt_ops"
+ * calls here.  We replace the native functions various "paravirt" structures
  * with our Guest versions, then boot like normal. :*/
 
 /*
@@ -97,29 +97,17 @@ static cycle_t clock_base;
  * them as a batch when lazy_mode is eventually turned off.  Because hypercalls
  * are reasonably expensive, batching them up makes sense.  For example, a
  * large mmap might update dozens of page table entries: that code calls
- * lguest_lazy_mode(PARAVIRT_LAZY_MMU), does the dozen updates, then calls
- * lguest_lazy_mode(PARAVIRT_LAZY_NONE).
+ * paravirt_enter_lazy_mmu(), does the dozen updates, then calls
+ * lguest_leave_lazy_mode().
  *
  * So, when we're in lazy mode, we call async_hypercall() to store the call for
  * future processing.  When lazy mode is turned off we issue a hypercall to
  * flush the stored calls.
- *
- * There's also a hack where "mode" is set to "PARAVIRT_LAZY_FLUSH" which
- * indicates we're to flush any outstanding calls immediately.  This is used
- * when an interrupt handler does a kmap_atomic(): the page table changes must
- * happen immediately even if we're in the middle of a batch.  Usually we're
- * not, though, so there's nothing to do. */
-static enum paravirt_lazy_mode lazy_mode; /* Note: not SMP-safe! */
-static void lguest_lazy_mode(enum paravirt_lazy_mode mode)
+ */
+static void lguest_leave_lazy_mode(void)
 {
-        if (mode == PARAVIRT_LAZY_FLUSH) {
-                if (unlikely(lazy_mode != PARAVIRT_LAZY_NONE))
-                        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
-        } else {
-                lazy_mode = mode;
-                if (mode == PARAVIRT_LAZY_NONE)
-                        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
-        }
+        paravirt_leave_lazy(paravirt_get_lazy_mode());
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
 }
 
 static void lazy_hcall(unsigned long call,
@@ -127,7 +115,7 @@ static void lazy_hcall(unsigned long call,
                        unsigned long arg2,
                        unsigned long arg3)
 {
-        if (lazy_mode == PARAVIRT_LAZY_NONE)
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
                 hcall(call, arg1, arg2, arg3);
         else
                 async_hcall(call, arg1, arg2, arg3);
@@ -331,7 +319,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu)
 }
 
 /*G:038 That's enough excitement for now, back to ploughing through each of
- * the paravirt_ops (we're about 1/3 of the way through).
+ * the different pv_ops structures (we're about 1/3 of the way through).
  *
  * This is the Local Descriptor Table, another weird Intel thingy.  Linux only
  * uses this for some strange applications like Wine.  We don't do anything
@@ -558,7 +546,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval)
                 lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0);
 }
 
-/* Unfortunately for Lguest, the paravirt_ops for page tables were based on
+/* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on
  * native page table operations.  On native hardware you can set a new page
  * table entry whenever you want, but if you want to remove one you have to do
  * a TLB flush (a TLB is a little cache of page table entries kept by the CPU).
@@ -782,7 +770,7 @@ static void lguest_time_init(void)
         clocksource_register(&lguest_clock);
 
         /* Now we've set up our clock, we can use it as the scheduler clock */
-        paravirt_ops.sched_clock = lguest_sched_clock;
+        pv_time_ops.sched_clock = lguest_sched_clock;
 
         /* We can't set cpumask in the initializer: damn C limitations!  Set it
          * here and register our timer device. */
@@ -904,7 +892,7 @@ static __init char *lguest_memory_setup(void)
 /*G:050
  * Patching (Powerfully Placating Performance Pedants)
  *
- * We have already seen that "struct paravirt_ops" lets us replace simple
+ * We have already seen that pv_ops structures let us replace simple
  * native instructions with calls to the appropriate back end all throughout
  * the kernel.  This allows the same kernel to run as a Guest and as a native
  * kernel, but it's slow because of all the indirect branches.
@@ -929,10 +917,10 @@ static const struct lguest_insns
 {
         const char *start, *end;
 } lguest_insns[] = {
-        [PARAVIRT_PATCH(irq_disable)] = { lgstart_cli, lgend_cli },
-        [PARAVIRT_PATCH(irq_enable)] = { lgstart_sti, lgend_sti },
-        [PARAVIRT_PATCH(restore_fl)] = { lgstart_popf, lgend_popf },
-        [PARAVIRT_PATCH(save_fl)] = { lgstart_pushf, lgend_pushf },
+        [PARAVIRT_PATCH(pv_irq_ops.irq_disable)] = { lgstart_cli, lgend_cli },
+        [PARAVIRT_PATCH(pv_irq_ops.irq_enable)] = { lgstart_sti, lgend_sti },
+        [PARAVIRT_PATCH(pv_irq_ops.restore_fl)] = { lgstart_popf, lgend_popf },
+        [PARAVIRT_PATCH(pv_irq_ops.save_fl)] = { lgstart_pushf, lgend_pushf },
 };
 
 /* Now our patch routine is fairly simple (based on the native one in
@@ -959,9 +947,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf,
         return insn_len;
 }
 
-/*G:030 Once we get to lguest_init(), we know we're a Guest.  The paravirt_ops
- * structure in the kernel provides a single point for (almost) every routine
- * we have to override to avoid privileged instructions. */
+/*G:030 Once we get to lguest_init(), we know we're a Guest.  The pv_ops
+ * structures in the kernel provide points for (almost) every routine we have
+ * to override to avoid privileged instructions. */
 __init void lguest_init(void *boot)
 {
         /* Copy boot parameters first: the Launcher put the physical location
@@ -976,54 +964,70 @@ __init void lguest_init(void *boot)
 
         /* We're under lguest, paravirt is enabled, and we're running at
          * privilege level 1, not 0 as normal. */
-        paravirt_ops.name = "lguest";
-        paravirt_ops.paravirt_enabled = 1;
-        paravirt_ops.kernel_rpl = 1;
+        pv_info.name = "lguest";
+        pv_info.paravirt_enabled = 1;
+        pv_info.kernel_rpl = 1;
 
         /* We set up all the lguest overrides for sensitive operations.  These
          * are detailed with the operations themselves. */
-        paravirt_ops.save_fl = save_fl;
-        paravirt_ops.restore_fl = restore_fl;
-        paravirt_ops.irq_disable = irq_disable;
-        paravirt_ops.irq_enable = irq_enable;
-        paravirt_ops.load_gdt = lguest_load_gdt;
-        paravirt_ops.memory_setup = lguest_memory_setup;
-        paravirt_ops.cpuid = lguest_cpuid;
-        paravirt_ops.write_cr3 = lguest_write_cr3;
-        paravirt_ops.flush_tlb_user = lguest_flush_tlb_user;
-        paravirt_ops.flush_tlb_single = lguest_flush_tlb_single;
-        paravirt_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
-        paravirt_ops.set_pte = lguest_set_pte;
-        paravirt_ops.set_pte_at = lguest_set_pte_at;
-        paravirt_ops.set_pmd = lguest_set_pmd;
+
+        /* interrupt-related operations */
+        pv_irq_ops.init_IRQ = lguest_init_IRQ;
+        pv_irq_ops.save_fl = save_fl;
+        pv_irq_ops.restore_fl = restore_fl;
+        pv_irq_ops.irq_disable = irq_disable;
+        pv_irq_ops.irq_enable = irq_enable;
+        pv_irq_ops.safe_halt = lguest_safe_halt;
+
+        /* init-time operations */
+        pv_init_ops.memory_setup = lguest_memory_setup;
+        pv_init_ops.patch = lguest_patch;
+
+        /* Intercepts of various cpu instructions */
+        pv_cpu_ops.load_gdt = lguest_load_gdt;
+        pv_cpu_ops.cpuid = lguest_cpuid;
+        pv_cpu_ops.load_idt = lguest_load_idt;
+        pv_cpu_ops.iret = lguest_iret;
+        pv_cpu_ops.load_esp0 = lguest_load_esp0;
+        pv_cpu_ops.load_tr_desc = lguest_load_tr_desc;
+        pv_cpu_ops.set_ldt = lguest_set_ldt;
+        pv_cpu_ops.load_tls = lguest_load_tls;
+        pv_cpu_ops.set_debugreg = lguest_set_debugreg;
+        pv_cpu_ops.clts = lguest_clts;
+        pv_cpu_ops.read_cr0 = lguest_read_cr0;
+        pv_cpu_ops.write_cr0 = lguest_write_cr0;
+        pv_cpu_ops.read_cr4 = lguest_read_cr4;
+        pv_cpu_ops.write_cr4 = lguest_write_cr4;
+        pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
+        pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
+        pv_cpu_ops.wbinvd = lguest_wbinvd;
+        pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
+        pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+
+        /* pagetable management */
+        pv_mmu_ops.write_cr3 = lguest_write_cr3;
+        pv_mmu_ops.flush_tlb_user = lguest_flush_tlb_user;
+        pv_mmu_ops.flush_tlb_single = lguest_flush_tlb_single;
+        pv_mmu_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
+        pv_mmu_ops.set_pte = lguest_set_pte;
+        pv_mmu_ops.set_pte_at = lguest_set_pte_at;
+        pv_mmu_ops.set_pmd = lguest_set_pmd;
+        pv_mmu_ops.read_cr2 = lguest_read_cr2;
+        pv_mmu_ops.read_cr3 = lguest_read_cr3;
+        pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
+        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+
 #ifdef CONFIG_X86_LOCAL_APIC
-        paravirt_ops.apic_write = lguest_apic_write;
-        paravirt_ops.apic_write_atomic = lguest_apic_write;
-        paravirt_ops.apic_read = lguest_apic_read;
+        /* apic read/write intercepts */
+        pv_apic_ops.apic_write = lguest_apic_write;
+        pv_apic_ops.apic_write_atomic = lguest_apic_write;
+        pv_apic_ops.apic_read = lguest_apic_read;
 #endif
-        paravirt_ops.load_idt = lguest_load_idt;
-        paravirt_ops.iret = lguest_iret;
-        paravirt_ops.load_esp0 = lguest_load_esp0;
-        paravirt_ops.load_tr_desc = lguest_load_tr_desc;
-        paravirt_ops.set_ldt = lguest_set_ldt;
-        paravirt_ops.load_tls = lguest_load_tls;
-        paravirt_ops.set_debugreg = lguest_set_debugreg;
-        paravirt_ops.clts = lguest_clts;
-        paravirt_ops.read_cr0 = lguest_read_cr0;
-        paravirt_ops.write_cr0 = lguest_write_cr0;
-        paravirt_ops.init_IRQ = lguest_init_IRQ;
-        paravirt_ops.read_cr2 = lguest_read_cr2;
-        paravirt_ops.read_cr3 = lguest_read_cr3;
-        paravirt_ops.read_cr4 = lguest_read_cr4;
-        paravirt_ops.write_cr4 = lguest_write_cr4;
-        paravirt_ops.write_gdt_entry = lguest_write_gdt_entry;
-        paravirt_ops.write_idt_entry = lguest_write_idt_entry;
-        paravirt_ops.patch = lguest_patch;
-        paravirt_ops.safe_halt = lguest_safe_halt;
-        paravirt_ops.get_wallclock = lguest_get_wallclock;
-        paravirt_ops.time_init = lguest_time_init;
-        paravirt_ops.set_lazy_mode = lguest_lazy_mode;
-        paravirt_ops.wbinvd = lguest_wbinvd;
+
+        /* time operations */
+        pv_time_ops.get_wallclock = lguest_get_wallclock;
+        pv_time_ops.time_init = lguest_time_init;
+
         /* Now is a good time to look at the implementations of these functions
          * before returning to the rest of lguest_init(). */
 
diff --git a/drivers/lguest/lguest_bus.c b/drivers/lguest/lguest_bus.c
index 9e7752cc8002..57329788f8a7 100644
--- a/drivers/lguest/lguest_bus.c
+++ b/drivers/lguest/lguest_bus.c
@@ -201,7 +201,7 @@ static void scan_devices(void)
  * "struct lguest_device_desc" array. */
 static int __init lguest_bus_init(void)
 {
-        if (strcmp(paravirt_ops.name, "lguest") != 0)
+        if (strcmp(pv_info.name, "lguest") != 0)
                 return 0;
 
         /* Devices are in a single page above top of "normal" mem */
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 65fe28860f54..68c0e3b2f0e8 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -213,7 +213,8 @@ static int mmc_read_ext_csd(struct mmc_card *card)
                 printk(KERN_ERR "%s: unrecognised EXT_CSD structure "
                         "version %d\n", mmc_hostname(card->host),
                         ext_csd_struct);
-                return -EINVAL;
+                err = -EINVAL;
+                goto out;
         }
 
         if (ext_csd_struct >= 2) {
diff --git a/drivers/mmc/host/at91_mci.c b/drivers/mmc/host/at91_mci.c
index 6ba98a49612d..7a452c2ad1f9 100644
--- a/drivers/mmc/host/at91_mci.c
+++ b/drivers/mmc/host/at91_mci.c
@@ -581,9 +581,7 @@ static void at91_mci_completed_command(struct at91mci_host *host)
         pr_debug("Status = %08X [%08X %08X %08X %08X]\n",
                  status, cmd->resp[0], cmd->resp[1], cmd->resp[2], cmd->resp[3]);
 
-        if (status & (AT91_MCI_RINDE | AT91_MCI_RDIRE | AT91_MCI_RCRCE |
-                        AT91_MCI_RENDE | AT91_MCI_RTOE | AT91_MCI_DCRCE |
-                        AT91_MCI_DTOE | AT91_MCI_OVRE | AT91_MCI_UNRE)) {
+        if (status & AT91_MCI_ERRORS) {
                 if ((status & AT91_MCI_RCRCE) && !(mmc_resp_type(cmd) & MMC_RSP_CRC)) {
                         cmd->error = 0;
                 }
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 5a6fdfd0f140..dae5c8d5a318 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -282,6 +282,12 @@ config LIBERTAS_CS
         ---help---
           A driver for Marvell Libertas 8385 CompactFlash devices.
 
+config LIBERTAS_SDIO
+        tristate "Marvell Libertas 8385 and 8686 SDIO 802.11b/g cards"
+        depends on LIBERTAS && MMC
+        ---help---
+          A driver for Marvell Libertas 8385 and 8686 SDIO devices.
+
 config LIBERTAS_DEBUG
         bool "Enable full debugging output in the Libertas module."
         depends on LIBERTAS
diff --git a/drivers/net/wireless/libertas/Makefile b/drivers/net/wireless/libertas/Makefile
index c469d569f090..0e2787691f96 100644
--- a/drivers/net/wireless/libertas/Makefile
+++ b/drivers/net/wireless/libertas/Makefile
@@ -7,7 +7,9 @@ libertas-objs := main.o wext.o \
 
 usb8xxx-objs += if_usb.o
 libertas_cs-objs += if_cs.o
+libertas_sdio-objs += if_sdio.o
 
 obj-$(CONFIG_LIBERTAS)     += libertas.o
 obj-$(CONFIG_LIBERTAS_USB) += usb8xxx.o
 obj-$(CONFIG_LIBERTAS_CS)  += libertas_cs.o
+obj-$(CONFIG_LIBERTAS_SDIO) += libertas_sdio.o
diff --git a/drivers/net/wireless/libertas/defs.h b/drivers/net/wireless/libertas/defs.h
index 7c5b7f7b45db..3a0c9beefcf8 100644
--- a/drivers/net/wireless/libertas/defs.h
+++ b/drivers/net/wireless/libertas/defs.h
@@ -39,6 +39,7 @@
 #define LBS_DEB_FW      0x00080000
 #define LBS_DEB_THREAD  0x00100000
 #define LBS_DEB_HEX     0x00200000
+#define LBS_DEB_SDIO    0x00400000
 
 extern unsigned int libertas_debug;
 
@@ -80,6 +81,7 @@ do { if ((libertas_debug & (grp)) == (grp)) \
 #define lbs_deb_usbd(dev, fmt, args...) LBS_DEB_LL(LBS_DEB_USB, " usbd", "%s:" fmt, (dev)->bus_id, ##args)
 #define lbs_deb_cs(fmt, args...)        LBS_DEB_LL(LBS_DEB_CS, " cs", fmt, ##args)
 #define lbs_deb_thread(fmt, args...)    LBS_DEB_LL(LBS_DEB_THREAD, " thread", fmt, ##args)
+#define lbs_deb_sdio(fmt, args...)      LBS_DEB_LL(LBS_DEB_SDIO, " thread", fmt, ##args)
 
 #define lbs_pr_info(format, args...) \
         printk(KERN_INFO DRV_NAME": " format, ## args)
diff --git a/drivers/net/wireless/libertas/if_sdio.c b/drivers/net/wireless/libertas/if_sdio.c
new file mode 100644
index 000000000000..a8e17076e7de
--- /dev/null
+++ b/drivers/net/wireless/libertas/if_sdio.c
@@ -0,0 +1,1079 @@
+/*
+ *  linux/drivers/net/wireless/libertas/if_sdio.c
+ *
+ *  Copyright 2007 Pierre Ossman
+ *
+ * Inspired by if_cs.c, Copyright 2007 Holger Schurig
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This hardware has more or less no CMD53 support, so all registers
+ * must be accessed using sdio_readb()/sdio_writeb().
+ *
+ * Transfers must be in one transaction or the firmware goes bonkers.
+ * This means that the transfer must either be small enough to do a
+ * byte based transfer or it must be padded to a multiple of the
+ * current block size.
+ *
+ * As SDIO is still new to the kernel, it is unfortunately common with
+ * bugs in the host controllers related to that. One such bug is that 
+ * controllers cannot do transfers that aren't a multiple of 4 bytes.
+ * If you don't have time to fix the host controller driver, you can
+ * work around the problem by modifying if_sdio_host_to_card() and
+ * if_sdio_card_to_host() to pad the data.
+ */
+
+#include <linux/moduleparam.h>
+#include <linux/firmware.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+#include <linux/mmc/sdio_ids.h>
+
+#include "host.h"
+#include "decl.h"
+#include "defs.h"
+#include "dev.h"
+#include "if_sdio.h"
+
+static char *libertas_helper_name = NULL;
+module_param_named(helper_name, libertas_helper_name, charp, 0644);
+
+static char *libertas_fw_name = NULL;
+module_param_named(fw_name, libertas_fw_name, charp, 0644);
+
+static const struct sdio_device_id if_sdio_ids[] = {
+        { SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_LIBERTAS) },
+        { /* end: all zeroes */                                         },
+};
+
+MODULE_DEVICE_TABLE(sdio, if_sdio_ids);
+
+struct if_sdio_model {
+        int model;
+        const char *helper;
+        const char *firmware;
+};
+
+static struct if_sdio_model if_sdio_models[] = {
+        {
+                /* 8385 */
+                .model = 0x04,
+                .helper = "sd8385_helper.bin",
+                .firmware = "sd8385.bin",
+        },
+        {
+                /* 8686 */
+                .model = 0x0B,
+                .helper = "sd8686_helper.bin",
+                .firmware = "sd8686.bin",
+        },
+};
+
+struct if_sdio_packet {
+        struct if_sdio_packet   *next;
+        u16                     nb;
+        u8                      buffer[0] __attribute__((aligned(4)));
+};
+
+struct if_sdio_card {
+        struct sdio_func        *func;
+        wlan_private            *priv;
+
+        int                     model;
+        unsigned long           ioport;
+
+        const char              *helper;
+        const char              *firmware;
+
+        u8                      buffer[65536];
+        u8                      int_cause;
+        u32                     event;
+
+        spinlock_t              lock;
+        struct if_sdio_packet   *packets;
+        struct work_struct      packet_worker;
+};
+
+/********************************************************************/
+/* I/O                                                              */
+/********************************************************************/
+
+static u16 if_sdio_read_scratch(struct if_sdio_card *card, int *err)
+{
+        int ret, reg;
+        u16 scratch;
+
+        if (card->model == 0x04)
+                reg = IF_SDIO_SCRATCH_OLD;
+        else
+                reg = IF_SDIO_SCRATCH;
+
+        scratch = sdio_readb(card->func, reg, &ret);
+        if (!ret)
+                scratch |= sdio_readb(card->func, reg + 1, &ret) << 8;
+
+        if (err)
+                *err = ret;
+
+        if (ret)
+                return 0xffff;
+
+        return scratch;
+}
+
+static int if_sdio_handle_cmd(struct if_sdio_card *card,
+                u8 *buffer, unsigned size)
+{
+        int ret;
+        unsigned long flags;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        spin_lock_irqsave(&card->priv->adapter->driver_lock, flags);
+
+        if (!card->priv->adapter->cur_cmd) {
+                lbs_deb_sdio("discarding spurious response\n");
+                ret = 0;
+                goto out;
+        }
+
+        if (size > MRVDRV_SIZE_OF_CMD_BUFFER) {
+                lbs_deb_sdio("response packet too large (%d bytes)\n",
+                        (int)size);
+                ret = -E2BIG;
+                goto out;
+        }
+
+        memcpy(card->priv->adapter->cur_cmd->bufvirtualaddr, buffer, size);
+        card->priv->upld_len = size;
+
+        card->int_cause |= MRVDRV_CMD_UPLD_RDY;
+
+        libertas_interrupt(card->priv->dev);
+
+        ret = 0;
+
+out:
+        spin_unlock_irqrestore(&card->priv->adapter->driver_lock, flags);
+
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_handle_data(struct if_sdio_card *card,
+                u8 *buffer, unsigned size)
+{
+        int ret;
+        struct sk_buff *skb;
+        char *data;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        if (size > MRVDRV_ETH_RX_PACKET_BUFFER_SIZE) {
+                lbs_deb_sdio("response packet too large (%d bytes)\n",
+                        (int)size);
+                ret = -E2BIG;
+                goto out;
+        }
+
+        skb = dev_alloc_skb(MRVDRV_ETH_RX_PACKET_BUFFER_SIZE);
+        if (!skb) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        data = skb_put(skb, size);
+
+        memcpy(data, buffer, size);
+
+        libertas_process_rxed_packet(card->priv, skb);
+
+        ret = 0;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_handle_event(struct if_sdio_card *card,
+                u8 *buffer, unsigned size)
+{
+        int ret;
+        unsigned long flags;
+        u32 event;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        if (card->model == 0x04) {
+                event = sdio_readb(card->func, IF_SDIO_EVENT, &ret);
+                if (ret)
+                        goto out;
+        } else {
+                if (size < 4) {
+                        lbs_deb_sdio("event packet too small (%d bytes)\n",
+                                (int)size);
+                        ret = -EINVAL;
+                        goto out;
+                }
+                event = buffer[3] << 24;
+                event |= buffer[2] << 16;
+                event |= buffer[1] << 8;
+                event |= buffer[0] << 0;
+                event <<= SBI_EVENT_CAUSE_SHIFT;
+        }
+
+        spin_lock_irqsave(&card->priv->adapter->driver_lock, flags);
+
+        card->event = event;
+        card->int_cause |= MRVDRV_CARDEVENT;
+
+        libertas_interrupt(card->priv->dev);
+
+        spin_unlock_irqrestore(&card->priv->adapter->driver_lock, flags);
+
+        ret = 0;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_card_to_host(struct if_sdio_card *card)
+{
+        int ret;
+        u8 status;
+        u16 size, type, chunk;
+        unsigned long timeout;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        size = if_sdio_read_scratch(card, &ret);
+        if (ret)
+                goto out;
+
+        if (size < 4) {
+                lbs_deb_sdio("invalid packet size (%d bytes) from firmware\n",
+                        (int)size);
+                ret = -EINVAL;
+                goto out;
+        }
+
+        timeout = jiffies + HZ;
+        while (1) {
+                status = sdio_readb(card->func, IF_SDIO_STATUS, &ret);
+                if (ret)
+                        goto out;
+                if (status & IF_SDIO_IO_RDY)
+                        break;
+                if (time_after(jiffies, timeout)) {
+                        ret = -ETIMEDOUT;
+                        goto out;
+                }
+                mdelay(1);
+        }
+
+        /*
+         * The transfer must be in one transaction or the firmware
+         * goes suicidal.
+         */
+        chunk = size;
+        if ((chunk > card->func->cur_blksize) || (chunk > 512)) {
+                chunk = (chunk + card->func->cur_blksize - 1) /
+                        card->func->cur_blksize * card->func->cur_blksize;
+        }
+
+        ret = sdio_readsb(card->func, card->buffer, card->ioport, chunk);
+        if (ret)
+                goto out;
+
+        chunk = card->buffer[0] | (card->buffer[1] << 8);
+        type = card->buffer[2] | (card->buffer[3] << 8);
+
+        lbs_deb_sdio("packet of type %d and size %d bytes\n",
+                (int)type, (int)chunk);
+
+        if (chunk > size) {
+                lbs_deb_sdio("packet fragment (%d > %d)\n",
+                        (int)chunk, (int)size);
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (chunk < size) {
+                lbs_deb_sdio("packet fragment (%d < %d)\n",
+                        (int)chunk, (int)size);
+        }
+
+        switch (type) {
+        case MVMS_CMD:
+                ret = if_sdio_handle_cmd(card, card->buffer + 4, chunk - 4);
+                if (ret)
+                        goto out;
+                break;
+        case MVMS_DAT:
+                ret = if_sdio_handle_data(card, card->buffer + 4, chunk - 4);
+                if (ret)
+                        goto out;
+                break;
+        case MVMS_EVENT:
+                ret = if_sdio_handle_event(card, card->buffer + 4, chunk - 4);
+                if (ret)
+                        goto out;
+                break;
+        default:
+                lbs_deb_sdio("invalid type (%d) from firmware\n",
+                                (int)type);
+                ret = -EINVAL;
+                goto out;
+        }
+
+out:
+        if (ret)
+                lbs_pr_err("problem fetching packet from firmware\n");
+
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static void if_sdio_host_to_card_worker(struct work_struct *work)
+{
+        struct if_sdio_card *card;
+        struct if_sdio_packet *packet;
+        unsigned long timeout;
+        u8 status;
+        int ret;
+        unsigned long flags;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        card = container_of(work, struct if_sdio_card, packet_worker);
+
+        while (1) {
+                spin_lock_irqsave(&card->lock, flags);
+                packet = card->packets;
+                if (packet)
+                        card->packets = packet->next;
+                spin_unlock_irqrestore(&card->lock, flags);
+
+                if (!packet)
+                        break;
+
+                sdio_claim_host(card->func);
+
+                timeout = jiffies + HZ;
+                while (1) {
+                        status = sdio_readb(card->func, IF_SDIO_STATUS, &ret);
+                        if (ret)
+                                goto release;
+                        if (status & IF_SDIO_IO_RDY)
+                                break;
+                        if (time_after(jiffies, timeout)) {
+                                ret = -ETIMEDOUT;
+                                goto release;
+                        }
+                        mdelay(1);
+                }
+
+                ret = sdio_writesb(card->func, card->ioport,
+                                packet->buffer, packet->nb);
+                if (ret)
+                        goto release;
+release:
+                sdio_release_host(card->func);
+
+                kfree(packet);
+        }
+
+        lbs_deb_leave(LBS_DEB_SDIO);
+}
+
+/********************************************************************/
+/* Firmware                                                         */
+/********************************************************************/
+
+static int if_sdio_prog_helper(struct if_sdio_card *card)
+{
+        int ret;
+        u8 status;
+        const struct firmware *fw;
+        unsigned long timeout;
+        u8 *chunk_buffer;
+        u32 chunk_size;
+        u8 *firmware;
+        size_t size;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        ret = request_firmware(&fw, card->helper, &card->func->dev);
+        if (ret) {
+                lbs_pr_err("can't load helper firmware\n");
+                goto out;
+        }
+
+        chunk_buffer = kzalloc(64, GFP_KERNEL);
+        if (!chunk_buffer) {
+                ret = -ENOMEM;
+                goto release_fw;
+        }
+
+        sdio_claim_host(card->func);
+
+        ret = sdio_set_block_size(card->func, 32);
+        if (ret)
+                goto release;
+
+        firmware = fw->data;
+        size = fw->size;
+
+        while (size) {
+                timeout = jiffies + HZ;
+                while (1) {
+                        status = sdio_readb(card->func, IF_SDIO_STATUS, &ret);
+                        if (ret)
+                                goto release;
+                        if ((status & IF_SDIO_IO_RDY) &&
+                                        (status & IF_SDIO_DL_RDY))
+                                break;
+                        if (time_after(jiffies, timeout)) {
+                                ret = -ETIMEDOUT;
+                                goto release;
+                        }
+                        mdelay(1);
+                }
+
+                chunk_size = min(size, (size_t)60);
+
+                *((u32*)chunk_buffer) = cpu_to_le32(chunk_size);
+                memcpy(chunk_buffer + 4, firmware, chunk_size);
+/*
+                lbs_deb_sdio("sending %d bytes chunk\n", chunk_size);
+*/
+                ret = sdio_writesb(card->func, card->ioport,
+                                chunk_buffer, 64);
+                if (ret)
+                        goto release;
+
+                firmware += chunk_size;
+                size -= chunk_size;
+        }
+
+        /* an empty block marks the end of the transfer */
+        memset(chunk_buffer, 0, 4);
+        ret = sdio_writesb(card->func, card->ioport, chunk_buffer, 64);
+        if (ret)
+                goto release;
+
+        lbs_deb_sdio("waiting for helper to boot...\n");
+
+        /* wait for the helper to boot by looking at the size register */
+        timeout = jiffies + HZ;
+        while (1) {
+                u16 req_size;
+
+                req_size = sdio_readb(card->func, IF_SDIO_RD_BASE, &ret);
+                if (ret)
+                        goto release;
+
+                req_size |= sdio_readb(card->func, IF_SDIO_RD_BASE + 1, &ret) << 8;
+                if (ret)
+                        goto release;
+
+                if (req_size != 0)
+                        break;
+
+                if (time_after(jiffies, timeout)) {
+                        ret = -ETIMEDOUT;
+                        goto release;
+                }
+
+                msleep(10);
+        }
+
+        ret = 0;
+
+release:
+        sdio_set_block_size(card->func, 0);
+        sdio_release_host(card->func);
+        kfree(chunk_buffer);
+release_fw:
+        release_firmware(fw);
+
+out:
+        if (ret)
+                lbs_pr_err("failed to load helper firmware\n");
+
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_prog_real(struct if_sdio_card *card)
+{
+        int ret;
+        u8 status;
+        const struct firmware *fw;
+        unsigned long timeout;
+        u8 *chunk_buffer;
+        u32 chunk_size;
+        u8 *firmware;
+        size_t size, req_size;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        ret = request_firmware(&fw, card->firmware, &card->func->dev);
+        if (ret) {
+                lbs_pr_err("can't load firmware\n");
+                goto out;
+        }
+
+        chunk_buffer = kzalloc(512, GFP_KERNEL);
+        if (!chunk_buffer) {
+                ret = -ENOMEM;
+                goto release_fw;
+        }
+
+        sdio_claim_host(card->func);
+
+        ret = sdio_set_block_size(card->func, 32);
+        if (ret)
+                goto release;
+
+        firmware = fw->data;
+        size = fw->size;
+
+        while (size) {
+                timeout = jiffies + HZ;
+                while (1) {
+                        status = sdio_readb(card->func, IF_SDIO_STATUS, &ret);
+                        if (ret)
+                                goto release;
+                        if ((status & IF_SDIO_IO_RDY) &&
+                                        (status & IF_SDIO_DL_RDY))
+                                break;
+                        if (time_after(jiffies, timeout)) {
+                                ret = -ETIMEDOUT;
+                                goto release;
+                        }
+                        mdelay(1);
+                }
+
+                req_size = sdio_readb(card->func, IF_SDIO_RD_BASE, &ret);
+                if (ret)
+                        goto release;
+
+                req_size |= sdio_readb(card->func, IF_SDIO_RD_BASE + 1, &ret) << 8;
+                if (ret)
+                        goto release;
+/*
+                lbs_deb_sdio("firmware wants %d bytes\n", (int)req_size);
+*/
+                if (req_size == 0) {
+                        lbs_deb_sdio("firmware helper gave up early\n");
+                        ret = -EIO;
+                        goto release;
+                }
+
+                if (req_size & 0x01) {
+                        lbs_deb_sdio("firmware helper signalled error\n");
+                        ret = -EIO;
+                        goto release;
+                }
+
+                if (req_size > size)
+                        req_size = size;
+
+                while (req_size) {
+                        chunk_size = min(req_size, (size_t)512);
+
+                        memcpy(chunk_buffer, firmware, chunk_size);
+/*
+                        lbs_deb_sdio("sending %d bytes (%d bytes) chunk\n",
+                                chunk_size, (chunk_size + 31) / 32 * 32);
+*/
+                        ret = sdio_writesb(card->func, card->ioport,
+                                chunk_buffer, (chunk_size + 31) / 32 * 32);
+                        if (ret)
+                                goto release;
+
+                        firmware += chunk_size;
+                        size -= chunk_size;
+                        req_size -= chunk_size;
+                }
+        }
+
+        ret = 0;
+
+        lbs_deb_sdio("waiting for firmware to boot...\n");
+
+        /* wait for the firmware to boot */
+        timeout = jiffies + HZ;
+        while (1) {
+                u16 scratch;
+
+                scratch = if_sdio_read_scratch(card, &ret);
+                if (ret)
+                        goto release;
+
+                if (scratch == IF_SDIO_FIRMWARE_OK)
+                        break;
+
+                if (time_after(jiffies, timeout)) {
+                        ret = -ETIMEDOUT;
+                        goto release;
+                }
+
+                msleep(10);
+        }
+
+        ret = 0;
+
+release:
+        sdio_set_block_size(card->func, 0);
+        sdio_release_host(card->func);
+        kfree(chunk_buffer);
+release_fw:
+        release_firmware(fw);
+
+out:
+        if (ret)
+                lbs_pr_err("failed to load firmware\n");
+
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_prog_firmware(struct if_sdio_card *card)
+{
+        int ret;
+        u16 scratch;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        sdio_claim_host(card->func);
+        scratch = if_sdio_read_scratch(card, &ret);
+        sdio_release_host(card->func);
+
+        if (ret)
+                goto out;
+
+        if (scratch == IF_SDIO_FIRMWARE_OK) {
+                lbs_deb_sdio("firmware already loaded\n");
+                goto success;
+        }
+
+        ret = if_sdio_prog_helper(card);
+        if (ret)
+                goto out;
+
+        ret = if_sdio_prog_real(card);
+        if (ret)
+                goto out;
+
+success:
+        ret = 0;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+/*******************************************************************/
+/* Libertas callbacks                                              */
+/*******************************************************************/
+
+static int if_sdio_host_to_card(wlan_private *priv, u8 type, u8 *buf, u16 nb)
+{
+        int ret;
+        struct if_sdio_card *card;
+        struct if_sdio_packet *packet, *cur;
+        u16 size;
+        unsigned long flags;
+
+        lbs_deb_enter_args(LBS_DEB_SDIO, "type %d, bytes %d", type, nb);
+
+        card = priv->card;
+
+        if (nb > (65536 - sizeof(struct if_sdio_packet) - 4)) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        /*
+         * The transfer must be in one transaction or the firmware
+         * goes suicidal.
+         */
+        size = nb + 4;
+        if ((size > card->func->cur_blksize) || (size > 512)) {
+                size = (size + card->func->cur_blksize - 1) /
+                        card->func->cur_blksize * card->func->cur_blksize;
+        }
+
+        packet = kzalloc(sizeof(struct if_sdio_packet) + size,
+                        GFP_ATOMIC);
+        if (!packet) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        packet->next = NULL;
+        packet->nb = size;
+
+        /*
+         * SDIO specific header.
+         */
+        packet->buffer[0] = (nb + 4) & 0xff;
+        packet->buffer[1] = ((nb + 4) >> 8) & 0xff;
+        packet->buffer[2] = type;
+        packet->buffer[3] = 0;
+
+        memcpy(packet->buffer + 4, buf, nb);
+
+        spin_lock_irqsave(&card->lock, flags);
+
+        if (!card->packets)
+                card->packets = packet;
+        else {
+                cur = card->packets;
+                while (cur->next)
+                        cur = cur->next;
+                cur->next = packet;
+        }
+
+        switch (type) {
+        case MVMS_CMD:
+                priv->dnld_sent = DNLD_CMD_SENT;
+                break;
+        case MVMS_DAT:
+                priv->dnld_sent = DNLD_DATA_SENT;
+                break;
+        default:
+                lbs_deb_sdio("unknown packet type %d\n", (int)type);
+        }
+
+        spin_unlock_irqrestore(&card->lock, flags);
+
+        schedule_work(&card->packet_worker);
+
+        ret = 0;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static int if_sdio_get_int_status(wlan_private *priv, u8 *ireg)
+{
+        struct if_sdio_card *card;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        card = priv->card;
+
+        *ireg = card->int_cause;
+        card->int_cause = 0;
+
+        lbs_deb_leave(LBS_DEB_SDIO);
+
+        return 0;
+}
+
+static int if_sdio_read_event_cause(wlan_private *priv)
+{
+        struct if_sdio_card *card;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        card = priv->card;
+
+        priv->adapter->eventcause = card->event;
+
+        lbs_deb_leave(LBS_DEB_SDIO);
+
+        return 0;
+}
+
+/*******************************************************************/
+/* SDIO callbacks                                                  */
+/*******************************************************************/
+
+static void if_sdio_interrupt(struct sdio_func *func)
+{
+        int ret;
+        struct if_sdio_card *card;
+        u8 cause;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        card = sdio_get_drvdata(func);
+
+        cause = sdio_readb(card->func, IF_SDIO_H_INT_STATUS, &ret);
+        if (ret)
+                goto out;
+
+        lbs_deb_sdio("interrupt: 0x%X\n", (unsigned)cause);
+
+        sdio_writeb(card->func, ~cause, IF_SDIO_H_INT_STATUS, &ret);
+        if (ret)
+                goto out;
+
+        /*
+         * Ignore the define name, this really means the card has
+         * successfully received the command.
+         */
+        if (cause & IF_SDIO_H_INT_DNLD) {
+                if ((card->priv->dnld_sent == DNLD_DATA_SENT) &&
+                        (card->priv->adapter->connect_status == LIBERTAS_CONNECTED))
+                        netif_wake_queue(card->priv->dev);
+                card->priv->dnld_sent = DNLD_RES_RECEIVED;
+        }
+
+        if (cause & IF_SDIO_H_INT_UPLD) {
+                ret = if_sdio_card_to_host(card);
+                if (ret)
+                        goto out;
+        }
+
+        ret = 0;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+}
+
+static int if_sdio_probe(struct sdio_func *func,
+                const struct sdio_device_id *id)
+{
+        struct if_sdio_card *card;
+        wlan_private *priv;
+        int ret, i;
+        unsigned int model;
+        struct if_sdio_packet *packet;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        for (i = 0;i < func->card->num_info;i++) {
+                if (sscanf(func->card->info[i],
+                                "802.11 SDIO ID: %x", &model) == 1)
+                        break;
+                if (sscanf(func->card->info[i],
+                                "ID: %x", &model) == 1)
+                        break;
+        }
+
+        if (i == func->card->num_info) {
+                lbs_pr_err("unable to identify card model\n");
+                return -ENODEV;
+        }
+
+        card = kzalloc(sizeof(struct if_sdio_card), GFP_KERNEL);
+        if (!card)
+                return -ENOMEM;
+
+        card->func = func;
+        card->model = model;
+        spin_lock_init(&card->lock);
+        INIT_WORK(&card->packet_worker, if_sdio_host_to_card_worker);
+
+        for (i = 0;i < ARRAY_SIZE(if_sdio_models);i++) {
+                if (card->model == if_sdio_models[i].model)
+                        break;
+        }
+
+        if (i == ARRAY_SIZE(if_sdio_models)) {
+                lbs_pr_err("unkown card model 0x%x\n", card->model);
+                ret = -ENODEV;
+                goto free;
+        }
+
+        card->helper = if_sdio_models[i].helper;
+        card->firmware = if_sdio_models[i].firmware;
+
+        if (libertas_helper_name) {
+                lbs_deb_sdio("overriding helper firmware: %s\n",
+                        libertas_helper_name);
+                card->helper = libertas_helper_name;
+        }
+
+        if (libertas_fw_name) {
+                lbs_deb_sdio("overriding firmware: %s\n", libertas_fw_name);
+                card->firmware = libertas_fw_name;
+        }
+
+        sdio_claim_host(func);
+
+        ret = sdio_enable_func(func);
+        if (ret)
+                goto release;
+
+        ret = sdio_claim_irq(func, if_sdio_interrupt);
+        if (ret)
+                goto disable;
+
+        card->ioport = sdio_readb(func, IF_SDIO_IOPORT, &ret);
+        if (ret)
+                goto release_int;
+
+        card->ioport |= sdio_readb(func, IF_SDIO_IOPORT + 1, &ret) << 8;
+        if (ret)
+                goto release_int;
+
+        card->ioport |= sdio_readb(func, IF_SDIO_IOPORT + 2, &ret) << 16;
+        if (ret)
+                goto release_int;
+
+        sdio_release_host(func);
+
+        sdio_set_drvdata(func, card);
+
+        lbs_deb_sdio("class = 0x%X, vendor = 0x%X, "
+                        "device = 0x%X, model = 0x%X, ioport = 0x%X\n",
+                        func->class, func->vendor, func->device,
+                        model, (unsigned)card->ioport);
+
+        ret = if_sdio_prog_firmware(card);
+        if (ret)
+                goto reclaim;
+
+        priv = libertas_add_card(card, &func->dev);
+        if (!priv) {
+                ret = -ENOMEM;
+                goto reclaim;
+        }
+
+        card->priv = priv;
+
+        priv->card = card;
+        priv->hw_host_to_card = if_sdio_host_to_card;
+        priv->hw_get_int_status = if_sdio_get_int_status;
+        priv->hw_read_event_cause = if_sdio_read_event_cause;
+
+        priv->adapter->fw_ready = 1;
+
+        /*
+         * Enable interrupts now that everything is set up
+         */
+        sdio_claim_host(func);
+        sdio_writeb(func, 0x0f, IF_SDIO_H_INT_MASK, &ret);
+        sdio_release_host(func);
+        if (ret)
+                goto reclaim;
+
+        ret = libertas_start_card(priv);
+        if (ret)
+                goto err_activate_card;
+
+out:
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+
+err_activate_card:
+        flush_scheduled_work();
+        free_netdev(priv->dev);
+        kfree(priv->adapter);
+reclaim:
+        sdio_claim_host(func);
+release_int:
+        sdio_release_irq(func);
+disable:
+        sdio_disable_func(func);
+release:
+        sdio_release_host(func);
+free:
+        while (card->packets) {
+                packet = card->packets;
+                card->packets = card->packets->next;
+                kfree(packet);
+        }
+
+        kfree(card);
+
+        goto out;
+}
+
+static void if_sdio_remove(struct sdio_func *func)
+{
+        struct if_sdio_card *card;
+        struct if_sdio_packet *packet;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        card = sdio_get_drvdata(func);
+
+        card->priv->adapter->surpriseremoved = 1;
+
+        lbs_deb_sdio("call remove card\n");
+        libertas_stop_card(card->priv);
+        libertas_remove_card(card->priv);
+
+        flush_scheduled_work();
+
+        sdio_claim_host(func);
+        sdio_release_irq(func);
+        sdio_disable_func(func);
+        sdio_release_host(func);
+
+        while (card->packets) {
+                packet = card->packets;
+                card->packets = card->packets->next;
+                kfree(packet);
+        }
+
+        kfree(card);
+
+        lbs_deb_leave(LBS_DEB_SDIO);
+}
+
+static struct sdio_driver if_sdio_driver = {
+        .name           = "libertas_sdio",
+        .id_table       = if_sdio_ids,
+        .probe          = if_sdio_probe,
+        .remove         = if_sdio_remove,
+};
+
+/*******************************************************************/
+/* Module functions                                                */
+/*******************************************************************/
+
+static int if_sdio_init_module(void)
+{
+        int ret = 0;
+
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        printk(KERN_INFO "libertas_sdio: Libertas SDIO driver\n");
+        printk(KERN_INFO "libertas_sdio: Copyright Pierre Ossman\n");
+
+        ret = sdio_register_driver(&if_sdio_driver);
+
+        lbs_deb_leave_args(LBS_DEB_SDIO, "ret %d", ret);
+
+        return ret;
+}
+
+static void if_sdio_exit_module(void)
+{
+        lbs_deb_enter(LBS_DEB_SDIO);
+
+        sdio_unregister_driver(&if_sdio_driver);
+
+        lbs_deb_leave(LBS_DEB_SDIO);
+}
+
+module_init(if_sdio_init_module);
+module_exit(if_sdio_exit_module);
+
+MODULE_DESCRIPTION("Libertas SDIO WLAN Driver");
+MODULE_AUTHOR("Pierre Ossman");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/libertas/if_sdio.h b/drivers/net/wireless/libertas/if_sdio.h
new file mode 100644
index 000000000000..dfcaea7b168f
--- /dev/null
+++ b/drivers/net/wireless/libertas/if_sdio.h
@@ -0,0 +1,45 @@
+/*
+ *  linux/drivers/net/wireless/libertas/if_sdio.h
+ *
+ *  Copyright 2007 Pierre Ossman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ */
+
+#ifndef LIBERTAS_IF_SDIO_H
+#define LIBERTAS_IF_SDIO_H
+
+#define IF_SDIO_IOPORT          0x00
+
+#define IF_SDIO_H_INT_MASK      0x04
+#define   IF_SDIO_H_INT_OFLOW   0x08
+#define   IF_SDIO_H_INT_UFLOW   0x04
+#define   IF_SDIO_H_INT_DNLD    0x02
+#define   IF_SDIO_H_INT_UPLD    0x01
+
+#define IF_SDIO_H_INT_STATUS    0x05
+#define IF_SDIO_H_INT_RSR       0x06
+#define IF_SDIO_H_INT_STATUS2   0x07
+
+#define IF_SDIO_RD_BASE         0x10
+
+#define IF_SDIO_STATUS          0x20
+#define   IF_SDIO_IO_RDY        0x08
+#define   IF_SDIO_CIS_RDY       0x04
+#define   IF_SDIO_UL_RDY        0x02
+#define   IF_SDIO_DL_RDY        0x01
+
+#define IF_SDIO_C_INT_MASK      0x24
+#define IF_SDIO_C_INT_STATUS    0x28
+#define IF_SDIO_C_INT_RSR       0x2C
+
+#define IF_SDIO_SCRATCH         0x34
+#define IF_SDIO_SCRATCH_OLD     0x80fe
+#define   IF_SDIO_FIRMWARE_OK   0xfedc
+
+#define IF_SDIO_EVENT           0x80fc
+
+#endif
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0c86be71bb33..aac8a02cbe80 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -764,6 +764,8 @@ struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask)
                 if (unlikely(!sgl))
                         goto enomem;
 
+                memset(sgl, 0, sizeof(*sgl) * sgp->size);
+
                 /*
                  * first loop through, set initial index and return value
                  */
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index efe474e2cc3b..b3bf4ecc983a 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -15,7 +15,6 @@ config VGASTATE
 
 config VIDEO_OUTPUT_CONTROL
         tristate "Lowlevel video output switch controls"
-        default m
         help
           This framework adds support for low-level control of the video 
           output switch.
diff --git a/include/asm-um/alternative-asm.i b/include/asm-um/alternative-asm.h
index cae9faca132f..9aa9fa2402a4 100644
--- a/include/asm-um/alternative-asm.i
+++ b/include/asm-um/alternative-asm.h
@@ -1,6 +1,6 @@
 #ifndef __UM_ALTERNATIVE_ASM_I
 #define __UM_ALTERNATIVE_ASM_I
 
-#include "asm/arch/alternative-asm.i"
+#include "asm/arch/alternative-asm.h"
 
 #endif
diff --git a/include/asm-um/frame.i b/include/asm-um/frame.h
index 09d5dca5d928..8a8c1cb415b4 100644
--- a/include/asm-um/frame.i
+++ b/include/asm-um/frame.h
@@ -1,6 +1,6 @@
 #ifndef __UM_FRAME_I
 #define __UM_FRAME_I
 
-#include "asm/arch/frame.i"
+#include "asm/arch/frame.h"
 
 #endif
diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild
index 80744dbcfafd..559830ece755 100644
--- a/include/asm-x86/Kbuild
+++ b/include/asm-x86/Kbuild
@@ -1,40 +1,22 @@
 include include/asm-generic/Kbuild.asm
 
 header-y += boot.h
-header-y += debugreg_32.h
-header-y += debugreg_64.h
 header-y += debugreg.h
-header-y += ldt_32.h
-header-y += ldt_64.h
 header-y += ldt.h
 header-y += msr-index.h
 header-y += prctl.h
-header-y += ptrace-abi_32.h
-header-y += ptrace-abi_64.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
-header-y += ucontext_32.h
-header-y += ucontext_64.h
 header-y += ucontext.h
 header-y += vsyscall32.h
 
 unifdef-y += a.out_32.h
 unifdef-y += a.out_64.h
-unifdef-y += auxvec_32.h
-unifdef-y += auxvec_64.h
 unifdef-y += byteorder_32.h
 unifdef-y += byteorder_64.h
 unifdef-y += elf_32.h
 unifdef-y += elf_64.h
-unifdef-y += errno_32.h
-unifdef-y += errno_64.h
-unifdef-y += ioctls_32.h
-unifdef-y += ioctls_64.h
-unifdef-y += ipcbuf_32.h
-unifdef-y += ipcbuf_64.h
 unifdef-y += mce.h
-unifdef-y += mman_32.h
-unifdef-y += mman_64.h
 unifdef-y += msgbuf_32.h
 unifdef-y += msgbuf_64.h
 unifdef-y += msr_32.h
@@ -45,40 +27,22 @@ unifdef-y += mtrr_64.h
 unifdef-y += mtrr.h
 unifdef-y += page_32.h
 unifdef-y += page_64.h
-unifdef-y += param_32.h
-unifdef-y += param_64.h
 unifdef-y += posix_types_32.h
 unifdef-y += posix_types_64.h
 unifdef-y += ptrace_32.h
 unifdef-y += ptrace_64.h
-unifdef-y += resource_32.h
-unifdef-y += resource_64.h
-unifdef-y += sembuf_32.h
-unifdef-y += sembuf_64.h
 unifdef-y += setup_32.h
 unifdef-y += setup_64.h
 unifdef-y += shmbuf_32.h
 unifdef-y += shmbuf_64.h
-unifdef-y += shmparam_32.h
-unifdef-y += shmparam_64.h
 unifdef-y += sigcontext_32.h
 unifdef-y += sigcontext_64.h
-unifdef-y += siginfo_32.h
-unifdef-y += siginfo_64.h
 unifdef-y += signal_32.h
 unifdef-y += signal_64.h
-unifdef-y += sockios_32.h
-unifdef-y += sockios_64.h
 unifdef-y += stat_32.h
 unifdef-y += stat_64.h
 unifdef-y += statfs_32.h
 unifdef-y += statfs_64.h
-unifdef-y += termbits_32.h
-unifdef-y += termbits_64.h
-unifdef-y += termios_32.h
-unifdef-y += termios_64.h
-unifdef-y += types_32.h
-unifdef-y += types_64.h
 unifdef-y += unistd_32.h
 unifdef-y += unistd_64.h
 unifdef-y += user_32.h
diff --git a/include/asm-x86/agp.h b/include/asm-x86/agp.h
index 9348f1e4f6f1..62df2a9e7130 100644
--- a/include/asm-x86/agp.h
+++ b/include/asm-x86/agp.h
@@ -1,5 +1,40 @@
-#ifdef CONFIG_X86_32
-# include "agp_32.h"
-#else
-# include "agp_64.h"
+#ifndef _ASM_X86_AGP_H
+#define _ASM_X86_AGP_H
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Functions to keep the agpgart mappings coherent with the MMU. The
+ * GART gives the CPU a physical alias of pages in memory. The alias
+ * region is mapped uncacheable. Make sure there are no conflicting
+ * mappings with different cachability attributes for the same
+ * page. This avoids data corruption on some CPUs.
+ */
+
+/*
+ * Caller's responsibility to call global_flush_tlb() for performance
+ * reasons
+ */
+#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
+#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
+#define flush_agp_mappings() global_flush_tlb()
+
+/*
+ * Could use CLFLUSH here if the cpu supports it. But then it would
+ * need to be called for each cacheline of the whole page so it may
+ * not be worth it. Would need a page for it.
+ */
+#define flush_agp_cache() wbinvd()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)         \
+        ((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)   \
+        free_pages((unsigned long)(table), (order))
+
 #endif
diff --git a/include/asm-x86/agp_32.h b/include/asm-x86/agp_32.h
deleted file mode 100644
index 6af173dbf123..000000000000
--- a/include/asm-x86/agp_32.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef AGP_H
-#define AGP_H 1
-
-#include <asm/pgtable.h>
-#include <asm/cacheflush.h>
-
-/* 
- * Functions to keep the agpgart mappings coherent with the MMU.
- * The GART gives the CPU a physical alias of pages in memory. The alias region is
- * mapped uncacheable. Make sure there are no conflicting mappings
- * with different cachability attributes for the same page. This avoids
- * data corruption on some CPUs.
- */
-
-/* Caller's responsibility to call global_flush_tlb() for
- * performance reasons */
-#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
-#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
-#define flush_agp_mappings() global_flush_tlb()
-
-/* Could use CLFLUSH here if the cpu supports it. But then it would
-   need to be called for each cacheline of the whole page so it may not be 
-   worth it. Would need a page for it. */
-#define flush_agp_cache() wbinvd()
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)         \
-        ((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)   \
-        free_pages((unsigned long)(table), (order))
-
-#endif
diff --git a/include/asm-x86/agp_64.h b/include/asm-x86/agp_64.h
deleted file mode 100644
index de338666f3f9..000000000000
--- a/include/asm-x86/agp_64.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef AGP_H
-#define AGP_H 1
-
-#include <asm/cacheflush.h>
-
-/* 
- * Functions to keep the agpgart mappings coherent.
- * The GART gives the CPU a physical alias of memory. The alias is
- * mapped uncacheable. Make sure there are no conflicting mappings
- * with different cachability attributes for the same page.
- */
-
-/* Caller's responsibility to call global_flush_tlb() for
- * performance reasons */
-#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
-#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
-#define flush_agp_mappings() global_flush_tlb()
-
-/* Could use CLFLUSH here if the cpu supports it. But then it would
-   need to be called for each cacheline of the whole page so it may not be 
-   worth it. Would need a page for it. */
-#define flush_agp_cache() asm volatile("wbinvd":::"memory")
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)         \
-        ((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)   \
-        free_pages((unsigned long)(table), (order))
-
-#endif
diff --git a/include/asm-x86/alternative-asm.h b/include/asm-x86/alternative-asm.h
new file mode 100644
index 000000000000..e2077d343c33
--- /dev/null
+++ b/include/asm-x86/alternative-asm.h
@@ -0,0 +1,22 @@
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_X86_32
+# define X86_ALIGN .long
+#else
+# define X86_ALIGN .quad
+#endif
+
+#ifdef CONFIG_SMP
+        .macro LOCK_PREFIX
+1:      lock
+        .section .smp_locks,"a"
+        .align 4
+        X86_ALIGN 1b
+        .previous
+        .endm
+#else
+        .macro LOCK_PREFIX
+        .endm
+#endif
+
+#endif  /*  __ASSEMBLY__  */
diff --git a/include/asm-x86/alternative-asm.i b/include/asm-x86/alternative-asm.i
deleted file mode 100644
index 4f360cd3c888..000000000000
--- a/include/asm-x86/alternative-asm.i
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "alternative-asm_32.i"
-#else
-# include "alternative-asm_64.i"
-#endif
diff --git a/include/asm-x86/alternative-asm_32.i b/include/asm-x86/alternative-asm_32.i
deleted file mode 100644
index f0510209ccbe..000000000000
--- a/include/asm-x86/alternative-asm_32.i
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifdef CONFIG_SMP
-        .macro LOCK_PREFIX
-1:      lock
-        .section .smp_locks,"a"
-        .align 4
-        .long 1b
-        .previous
-        .endm
-#else
-        .macro LOCK_PREFIX
-        .endm
-#endif
diff --git a/include/asm-x86/alternative-asm_64.i b/include/asm-x86/alternative-asm_64.i
deleted file mode 100644
index 0b3f1a2bb2cb..000000000000
--- a/include/asm-x86/alternative-asm_64.i
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifdef CONFIG_SMP
-        .macro LOCK_PREFIX
-1:      lock
-        .section .smp_locks,"a"
-        .align 8
-        .quad 1b
-        .previous
-        .endm
-#else
-        .macro LOCK_PREFIX
-        .endm
-#endif
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
index f2e64634fa48..2d20a7a19f62 100644
--- a/include/asm-x86/atomic_64.h
+++ b/include/asm-x86/atomic_64.h
@@ -206,7 +206,7 @@ static __inline__ int atomic_sub_return(int i, atomic_t *v)
 
 /* An 64bit atomic type */
 
-typedef struct { volatile long counter; } atomic64_t;
+typedef struct { long counter; } atomic64_t;
 
 #define ATOMIC64_INIT(i)        { (i) }
 
diff --git a/include/asm-x86/auxvec.h b/include/asm-x86/auxvec.h
index 7ff866f829ca..87f5e6d5a020 100644
--- a/include/asm-x86/auxvec.h
+++ b/include/asm-x86/auxvec.h
@@ -1,13 +1,12 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "auxvec_32.h"
-# else
-#  include "auxvec_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "auxvec_32.h"
-# else
-#  include "auxvec_64.h"
-# endif
+#ifndef _ASM_X86_AUXVEC_H
+#define _ASM_X86_AUXVEC_H
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#ifdef __i386__
+#define AT_SYSINFO              32
+#endif
+#define AT_SYSINFO_EHDR         33
+
 #endif
diff --git a/include/asm-x86/auxvec_32.h b/include/asm-x86/auxvec_32.h
deleted file mode 100644
index 395e13016bfb..000000000000
--- a/include/asm-x86/auxvec_32.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __ASMi386_AUXVEC_H
-#define __ASMi386_AUXVEC_H
-
-/*
- * Architecture-neutral AT_ values in 0-17, leave some room
- * for more of them, start the x86-specific ones at 32.
- */
-#define AT_SYSINFO              32
-#define AT_SYSINFO_EHDR         33
-
-#endif
diff --git a/include/asm-x86/auxvec_64.h b/include/asm-x86/auxvec_64.h
deleted file mode 100644
index 1d5ab0d03950..000000000000
--- a/include/asm-x86/auxvec_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_X86_64_AUXVEC_H
-#define __ASM_X86_64_AUXVEC_H
-
-#define AT_SYSINFO_EHDR         33
-
-#endif
diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h
index d4dbbe5f7bd9..1d7d9b4bcacb 100644
--- a/include/asm-x86/bitops_64.h
+++ b/include/asm-x86/bitops_64.h
@@ -260,7 +260,7 @@ extern long find_first_bit(const unsigned long * addr, unsigned long size);
 extern long find_next_bit(const unsigned long * addr, long size, long offset);
 
 /* return index of first bet set in val or max when no bit is set */
-static inline unsigned long __scanbit(unsigned long val, unsigned long max)
+static inline long __scanbit(unsigned long val, unsigned long max)
 {
         asm("bsfq %1,%0 ; cmovz %2,%0" : "=&r" (val) : "r" (val), "r" (max));
         return val;
diff --git a/include/asm-x86/bug.h b/include/asm-x86/bug.h
index c655d7f3a5e0..fd8bdc639c48 100644
--- a/include/asm-x86/bug.h
+++ b/include/asm-x86/bug.h
@@ -1,5 +1,42 @@
+#ifndef _ASM_X86_BUG_H
+#define _ASM_X86_BUG_H
+
+#ifdef CONFIG_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
 #ifdef CONFIG_X86_32
-# include "bug_32.h"
+# define __BUG_C0       "2:\t.long 1b, %c0\n"
 #else
-# include "bug_64.h"
+# define __BUG_C0       "2:\t.quad 1b, %c0\n"
+#endif
+
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("1:\tud2\n"                                \
+                             ".pushsection __bug_table,\"a\"\n"         \
+                             __BUG_C0                                   \
+                             "\t.word %c1, 0\n"                         \
+                             "\t.org 2b+%c2\n"                          \
+                             ".popsection"                              \
+                             : : "i" (__FILE__), "i" (__LINE__),        \
+                             "i" (sizeof(struct bug_entry)));           \
+                for(;;) ;                                               \
+        } while(0)
+
+#else
+#define BUG()                                                           \
+        do {                                                            \
+                asm volatile("ud2");                                    \
+                for(;;) ;                                               \
+        } while(0)
+#endif
+
+void out_of_line_bug(void);
+#else /* CONFIG_BUG */
+static inline void out_of_line_bug(void) { }
+#endif /* !CONFIG_BUG */
+
+#include <asm-generic/bug.h>
 #endif
diff --git a/include/asm-x86/bug_32.h b/include/asm-x86/bug_32.h
deleted file mode 100644
index b0fd78ca2619..000000000000
--- a/include/asm-x86/bug_32.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef _I386_BUG_H
-#define _I386_BUG_H
-
-
-/*
- * Tell the user there is some problem.
- * The offending file and line are encoded encoded in the __bug_table section.
- */
-
-#ifdef CONFIG_BUG
-#define HAVE_ARCH_BUG
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#define BUG()                                                           \
-        do {                                                            \
-                asm volatile("1:\tud2\n"                                \
-                             ".pushsection __bug_table,\"a\"\n"         \
-                             "2:\t.long 1b, %c0\n"                      \
-                             "\t.word %c1, 0\n"                         \
-                             "\t.org 2b+%c2\n"                          \
-                             ".popsection"                              \
-                             : : "i" (__FILE__), "i" (__LINE__),        \
-                             "i" (sizeof(struct bug_entry)));           \
-                for(;;) ;                                               \
-        } while(0)
-
-#else
-#define BUG()                                                           \
-        do {                                                            \
-                asm volatile("ud2");                                    \
-                for(;;) ;                                               \
-        } while(0)
-#endif
-#endif
-
-#include <asm-generic/bug.h>
-#endif
diff --git a/include/asm-x86/bug_64.h b/include/asm-x86/bug_64.h
deleted file mode 100644
index 682606414913..000000000000
--- a/include/asm-x86/bug_64.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ASM_X8664_BUG_H
-#define __ASM_X8664_BUG_H 1
-
-#ifdef CONFIG_BUG
-#define HAVE_ARCH_BUG
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#define BUG()                                                           \
-        do {                                                            \
-                asm volatile("1:\tud2\n"                                \
-                             ".pushsection __bug_table,\"a\"\n"         \
-                             "2:\t.quad 1b, %c0\n"                      \
-                             "\t.word %c1, 0\n"                         \
-                             "\t.org 2b+%c2\n"                          \
-                             ".popsection"                              \
-                             : : "i" (__FILE__), "i" (__LINE__),        \
-                                "i" (sizeof(struct bug_entry)));        \
-                for(;;) ;                                               \
-        } while(0)
-#else
-#define BUG()                                                           \
-        do {                                                            \
-                asm volatile("ud2");                                    \
-                for(;;) ;                                               \
-        } while(0)
-#endif
-
-void out_of_line_bug(void);
-#else
-static inline void out_of_line_bug(void) { }
-#endif
-
-#include <asm-generic/bug.h>
-#endif
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index ddf42d36dd50..aac8317420af 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -1,5 +1,6 @@
-#ifdef CONFIG_X86_32
-# include "bugs_32.h"
-#else
-# include "bugs_64.h"
-#endif
+#ifndef _ASM_X86_BUGS_H
+#define _ASM_X86_BUGS_H
+
+void check_bugs(void);
+
+#endif /* _ASM_X86_BUGS_H */
diff --git a/include/asm-x86/bugs_32.h b/include/asm-x86/bugs_32.h
deleted file mode 100644
index d28979ff73be..000000000000
--- a/include/asm-x86/bugs_32.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *      void check_bugs(void);
- */
-#ifndef _ASM_I386_BUG_H
-#define _ASM_I386_BUG_H
-
-void check_bugs(void);
-
-#endif  /* _ASM_I386_BUG_H */
diff --git a/include/asm-x86/bugs_64.h b/include/asm-x86/bugs_64.h
deleted file mode 100644
index b33dc04d8f42..000000000000
--- a/include/asm-x86/bugs_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_X86_64_BUGS_H
-#define _ASM_X86_64_BUGS_H
-
-void check_bugs(void);
-
-#endif  /* _ASM_X86_64_BUGS_H */
diff --git a/include/asm-x86/cache.h b/include/asm-x86/cache.h
index c36d190ac9d8..1e0bac86f38f 100644
--- a/include/asm-x86/cache.h
+++ b/include/asm-x86/cache.h
@@ -1,5 +1,20 @@
-#ifdef CONFIG_X86_32
-# include "cache_32.h"
-#else
-# include "cache_64.h"
+#ifndef _ARCH_X86_CACHE_H
+#define _ARCH_X86_CACHE_H
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
+
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
+#ifdef CONFIG_X86_VSMP
+/* vSMP Internode cacheline shift */
+#define INTERNODE_CACHE_SHIFT (12)
+#ifdef CONFIG_SMP
+#define __cacheline_aligned_in_smp                                      \
+        __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))      \
+        __attribute__((__section__(".data.page_aligned")))
+#endif
+#endif
+
 #endif
diff --git a/include/asm-x86/cache_32.h b/include/asm-x86/cache_32.h
deleted file mode 100644
index 57c62f414158..000000000000
--- a/include/asm-x86/cache_32.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * include/asm-i386/cache.h
- */
-#ifndef __ARCH_I386_CACHE_H
-#define __ARCH_I386_CACHE_H
-
-
-/* L1 cache line size */
-#define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
-#define L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
-
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-
-#endif
diff --git a/include/asm-x86/cache_64.h b/include/asm-x86/cache_64.h
deleted file mode 100644
index 052df758ae61..000000000000
--- a/include/asm-x86/cache_64.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * include/asm-x86_64/cache.h
- */
-#ifndef __ARCH_X8664_CACHE_H
-#define __ARCH_X8664_CACHE_H
-
-
-/* L1 cache line size */
-#define L1_CACHE_SHIFT  (CONFIG_X86_L1_CACHE_SHIFT)
-#define L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
-
-#ifdef CONFIG_X86_VSMP
-
-/* vSMP Internode cacheline shift */
-#define INTERNODE_CACHE_SHIFT (12)
-#ifdef CONFIG_SMP
-#define __cacheline_aligned_in_smp                                      \
-       __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))         \
-       __attribute__((__section__(".data.page_aligned")))
-#endif
-
-#endif
-
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-
-#endif
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
index e2df3b55034a..b3d43de44c59 100644
--- a/include/asm-x86/cacheflush.h
+++ b/include/asm-x86/cacheflush.h
@@ -1,5 +1,40 @@
-#ifdef CONFIG_X86_32
-# include "cacheflush_32.h"
-#else
-# include "cacheflush_64.h"
+#ifndef _ASM_X86_CACHEFLUSH_H
+#define _ASM_X86_CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all()                       do { } while (0)
+#define flush_cache_mm(mm)                      do { } while (0)
+#define flush_cache_dup_mm(mm)                  do { } while (0)
+#define flush_cache_range(vma, start, end)      do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
+#define flush_dcache_page(page)                 do { } while (0)
+#define flush_dcache_mmap_lock(mapping)         do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
+#define flush_icache_range(start, end)          do { } while (0)
+#define flush_icache_page(vma,pg)               do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
+#define flush_cache_vmap(start, end)            do { } while (0)
+#define flush_cache_vunmap(start, end)          do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+        memcpy(dst, src, len)
+
+void global_flush_tlb(void);
+int change_page_attr(struct page *page, int numpages, pgprot_t prot);
+int change_page_attr_addr(unsigned long addr, int numpages, pgprot_t prot);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+/* internal debugging function */
+void kernel_map_pages(struct page *page, int numpages, int enable);
+#endif
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
 #endif
diff --git a/include/asm-x86/cacheflush_32.h b/include/asm-x86/cacheflush_32.h
deleted file mode 100644
index 74e03c8f2e51..000000000000
--- a/include/asm-x86/cacheflush_32.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef _I386_CACHEFLUSH_H
-#define _I386_CACHEFLUSH_H
-
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
-/* Caches aren't brain-dead on the intel. */
-#define flush_cache_all()                       do { } while (0)
-#define flush_cache_mm(mm)                      do { } while (0)
-#define flush_cache_dup_mm(mm)                  do { } while (0)
-#define flush_cache_range(vma, start, end)      do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
-#define flush_dcache_page(page)                 do { } while (0)
-#define flush_dcache_mmap_lock(mapping)         do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
-#define flush_icache_range(start, end)          do { } while (0)
-#define flush_icache_page(vma,pg)               do { } while (0)
-#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
-#define flush_cache_vmap(start, end)            do { } while (0)
-#define flush_cache_vunmap(start, end)          do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-        memcpy(dst, src, len)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-        memcpy(dst, src, len)
-
-void global_flush_tlb(void); 
-int change_page_attr(struct page *page, int numpages, pgprot_t prot);
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-/* internal debugging function */
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
-#endif /* _I386_CACHEFLUSH_H */
diff --git a/include/asm-x86/cacheflush_64.h b/include/asm-x86/cacheflush_64.h
deleted file mode 100644
index ab1cb5c7dc92..000000000000
--- a/include/asm-x86/cacheflush_64.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef _X8664_CACHEFLUSH_H
-#define _X8664_CACHEFLUSH_H
-
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
-/* Caches aren't brain-dead on the intel. */
-#define flush_cache_all()                       do { } while (0)
-#define flush_cache_mm(mm)                      do { } while (0)
-#define flush_cache_dup_mm(mm)                  do { } while (0)
-#define flush_cache_range(vma, start, end)      do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)      do { } while (0)
-#define flush_dcache_page(page)                 do { } while (0)
-#define flush_dcache_mmap_lock(mapping)         do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)       do { } while (0)
-#define flush_icache_range(start, end)          do { } while (0)
-#define flush_icache_page(vma,pg)               do { } while (0)
-#define flush_icache_user_range(vma,pg,adr,len) do { } while (0)
-#define flush_cache_vmap(start, end)            do { } while (0)
-#define flush_cache_vunmap(start, end)          do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-        memcpy(dst, src, len)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-        memcpy(dst, src, len)
-
-void global_flush_tlb(void); 
-int change_page_attr(struct page *page, int numpages, pgprot_t prot);
-int change_page_attr_addr(unsigned long addr, int numpages, pgprot_t prot);
-
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
-#endif /* _X8664_CACHEFLUSH_H */
diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h
index 9d914e1e4aad..b1bc7b1b64b0 100644
--- a/include/asm-x86/cpu.h
+++ b/include/asm-x86/cpu.h
@@ -13,9 +13,6 @@ struct i386_cpu {
 extern int arch_register_cpu(int num);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void arch_unregister_cpu(int);
-extern int enable_cpu_hotplug;
-#else
-#define enable_cpu_hotplug      0
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
diff --git a/include/asm-x86/cputime.h b/include/asm-x86/cputime.h
index 87c37cf6b707..6d68ad7e0ea3 100644
--- a/include/asm-x86/cputime.h
+++ b/include/asm-x86/cputime.h
@@ -1,5 +1 @@
-#ifdef CONFIG_X86_32
-# include "cputime_32.h"
-#else
-# include "cputime_64.h"
-#endif
+#include <asm-generic/cputime.h>
diff --git a/include/asm-x86/cputime_32.h b/include/asm-x86/cputime_32.h
deleted file mode 100644
index 398ed7cd171d..000000000000
--- a/include/asm-x86/cputime_32.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __I386_CPUTIME_H
-#define __I386_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __I386_CPUTIME_H */
diff --git a/include/asm-x86/cputime_64.h b/include/asm-x86/cputime_64.h
deleted file mode 100644
index a07012dc5a3c..000000000000
--- a/include/asm-x86/cputime_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __X86_64_CPUTIME_H
-#define __X86_64_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __X86_64_CPUTIME_H */
diff --git a/include/asm-x86/debugreg.h b/include/asm-x86/debugreg.h
index b6ce7e4fa002..c6344d572b03 100644
--- a/include/asm-x86/debugreg.h
+++ b/include/asm-x86/debugreg.h
@@ -1,13 +1,70 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "debugreg_32.h"
-# else
-#  include "debugreg_64.h"
-# endif
+#ifndef _ASM_X86_DEBUGREG_H
+#define _ASM_X86_DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
+
+#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
+#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register.  We can use this to determine
+   which debugging register was responsible for the trap.  The other bits
+   are either reserved or not of interest to us. */
+
+#define DR_TRAP0        (0x1)           /* db0 */
+#define DR_TRAP1        (0x2)           /* db1 */
+#define DR_TRAP2        (0x4)           /* db2 */
+#define DR_TRAP3        (0x8)           /* db3 */
+
+#define DR_STEP         (0x4000)        /* single-step */
+#define DR_SWITCH       (0x8000)        /* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+   The top two bytes of the control register consist of 4 fields of 4
+   bits - each field corresponds to one of the four debug registers,
+   and indicates what types of access we trap on, and how large the data
+   field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+#define DR_LEN_8 (0x8)
+
+/* The low byte to the control register determine which registers are
+   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
+   that the processor will reset the bit after a task switch and the other
+   is global meaning that we have to explicitly reset the bit.  With linux,
+   you can use either one, since we explicitly zero the register when we enter
+   kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+   We can slow the instruction pipeline for instructions coming via the
+   gdt or the ldt if we want to.  I am not sure why this is an advantage */
+
+#ifdef __i386__
+#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
 #else
-# ifdef __i386__
-#  include "debugreg_32.h"
-# else
-#  include "debugreg_64.h"
-# endif
+#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
+#endif
+
+#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
+
 #endif
diff --git a/include/asm-x86/debugreg_32.h b/include/asm-x86/debugreg_32.h
deleted file mode 100644
index f0b2b06ae0f7..000000000000
--- a/include/asm-x86/debugreg_32.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef _I386_DEBUGREG_H
-#define _I386_DEBUGREG_H
-
-
-/* Indicate the register numbers for a number of the specific
-   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
-#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
-#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
-
-#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
-#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
-
-/* Define a few things for the status register.  We can use this to determine
-   which debugging register was responsible for the trap.  The other bits
-   are either reserved or not of interest to us. */
-
-#define DR_TRAP0        (0x1)           /* db0 */
-#define DR_TRAP1        (0x2)           /* db1 */
-#define DR_TRAP2        (0x4)           /* db2 */
-#define DR_TRAP3        (0x8)           /* db3 */
-
-#define DR_STEP         (0x4000)        /* single-step */
-#define DR_SWITCH       (0x8000)        /* task switch */
-
-/* Now define a bunch of things for manipulating the control register.
-   The top two bytes of the control register consist of 4 fields of 4
-   bits - each field corresponds to one of the four debug registers,
-   and indicates what types of access we trap on, and how large the data
-   field is that we are looking at */
-
-#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
-#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
-
-#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
-#define DR_RW_WRITE (0x1)
-#define DR_RW_READ (0x3)
-
-#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
-#define DR_LEN_2 (0x4)
-#define DR_LEN_4 (0xC)
-
-/* The low byte to the control register determine which registers are
-   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
-   that the processor will reset the bit after a task switch and the other
-   is global meaning that we have to explicitly reset the bit.  With linux,
-   you can use either one, since we explicitly zero the register when we enter
-   kernel mode. */
-
-#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
-#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
-#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
-
-#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
-#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
-
-/* The second byte to the control register has a few special things.
-   We can slow the instruction pipeline for instructions coming via the
-   gdt or the ldt if we want to.  I am not sure why this is an advantage */
-
-#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
-#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
-#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
-
-#endif
diff --git a/include/asm-x86/debugreg_64.h b/include/asm-x86/debugreg_64.h
deleted file mode 100644
index bd1aab1d8c4a..000000000000
--- a/include/asm-x86/debugreg_64.h
+++ /dev/null
@@ -1,65 +0,0 @@
-#ifndef _X86_64_DEBUGREG_H
-#define _X86_64_DEBUGREG_H
-
-
-/* Indicate the register numbers for a number of the specific
-   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
-#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
-#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
-
-#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
-#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
-
-/* Define a few things for the status register.  We can use this to determine
-   which debugging register was responsible for the trap.  The other bits
-   are either reserved or not of interest to us. */
-
-#define DR_TRAP0        (0x1)           /* db0 */
-#define DR_TRAP1        (0x2)           /* db1 */
-#define DR_TRAP2        (0x4)           /* db2 */
-#define DR_TRAP3        (0x8)           /* db3 */
-
-#define DR_STEP         (0x4000)        /* single-step */
-#define DR_SWITCH       (0x8000)        /* task switch */
-
-/* Now define a bunch of things for manipulating the control register.
-   The top two bytes of the control register consist of 4 fields of 4
-   bits - each field corresponds to one of the four debug registers,
-   and indicates what types of access we trap on, and how large the data
-   field is that we are looking at */
-
-#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
-#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
-
-#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
-#define DR_RW_WRITE (0x1)
-#define DR_RW_READ (0x3)
-
-#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
-#define DR_LEN_2 (0x4)
-#define DR_LEN_4 (0xC)
-#define DR_LEN_8 (0x8)
-
-/* The low byte to the control register determine which registers are
-   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
-   that the processor will reset the bit after a task switch and the other
-   is global meaning that we have to explicitly reset the bit.  With linux,
-   you can use either one, since we explicitly zero the register when we enter
-   kernel mode. */
-
-#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
-#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
-#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
-
-#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
-#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
-
-/* The second byte to the control register has a few special things.
-   We can slow the instruction pipeline for instructions coming via the
-   gdt or the ldt if we want to.  I am not sure why this is an advantage */
-
-#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
-#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
-#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
-
-#endif
diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h
index 10f2c71d622b..d11d47fc1a0e 100644
--- a/include/asm-x86/delay.h
+++ b/include/asm-x86/delay.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "delay_32.h"
-#else
-# include "delay_64.h"
-#endif
+#ifndef _ASM_X86_DELAY_H
+#define _ASM_X86_DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/x86/lib/delay.c
+ */
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n) (__builtin_constant_p(n) ? \
+        ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
+        __udelay(n))
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n) (__builtin_constant_p(n) ? \
+        ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+        __ndelay(n))
+
+void use_tsc_delay(void);
+
+#endif /* _ASM_X86_DELAY_H */
diff --git a/include/asm-x86/delay_32.h b/include/asm-x86/delay_32.h
deleted file mode 100644
index 9ae5e3782ed8..000000000000
--- a/include/asm-x86/delay_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _I386_DELAY_H
-#define _I386_DELAY_H
-
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines calling functions in arch/i386/lib/delay.c
- */
- 
-/* Undefined functions to get compile-time errors */
-extern void __bad_udelay(void);
-extern void __bad_ndelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __ndelay(unsigned long nsecs);
-extern void __const_udelay(unsigned long usecs);
-extern void __delay(unsigned long loops);
-
-/* 0x10c7 is 2**32 / 1000000 (rounded up) */
-#define udelay(n) (__builtin_constant_p(n) ? \
-        ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
-        __udelay(n))
-
-/* 0x5 is 2**32 / 1000000000 (rounded up) */
-#define ndelay(n) (__builtin_constant_p(n) ? \
-        ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
-        __ndelay(n))
-
-void use_tsc_delay(void);
-
-#endif /* defined(_I386_DELAY_H) */
diff --git a/include/asm-x86/delay_64.h b/include/asm-x86/delay_64.h
deleted file mode 100644
index c2669f1f5529..000000000000
--- a/include/asm-x86/delay_64.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _X8664_DELAY_H
-#define _X8664_DELAY_H
-
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines calling functions in arch/x86_64/lib/delay.c
- */
- 
-/* Undefined functions to get compile-time errors */
-extern void __bad_udelay(void);
-extern void __bad_ndelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __ndelay(unsigned long nsecs);
-extern void __const_udelay(unsigned long usecs);
-extern void __delay(unsigned long loops);
-
-/* 0x10c7 is 2**32 / 1000000 (rounded up) */
-#define udelay(n) (__builtin_constant_p(n) ? \
-        ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
-        __udelay(n))
-
-/* 0x5 is 2**32 / 1000000000 (rounded up) */
-#define ndelay(n) (__builtin_constant_p(n) ? \
-       ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
-       __ndelay(n))
-
-
-#endif /* defined(_X8664_DELAY_H) */
diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h
index e2bcf7c7dcee..d9ee5e52e91b 100644
--- a/include/asm-x86/device.h
+++ b/include/asm-x86/device.h
@@ -1,5 +1,10 @@
-#ifdef CONFIG_X86_32
-# include "device_32.h"
-#else
-# include "device_64.h"
+#ifndef _ASM_X86_DEVICE_H
+#define _ASM_X86_DEVICE_H
+
+struct dev_archdata {
+#ifdef CONFIG_ACPI
+        void    *acpi_handle;
 #endif
+};
+
+#endif /* _ASM_X86_DEVICE_H */
diff --git a/include/asm-x86/device_32.h b/include/asm-x86/device_32.h
deleted file mode 100644
index 849604c70e6b..000000000000
--- a/include/asm-x86/device_32.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#ifndef _ASM_I386_DEVICE_H
-#define _ASM_I386_DEVICE_H
-
-struct dev_archdata {
-#ifdef CONFIG_ACPI
-        void    *acpi_handle;
-#endif
-};
-
-#endif /* _ASM_I386_DEVICE_H */
diff --git a/include/asm-x86/device_64.h b/include/asm-x86/device_64.h
deleted file mode 100644
index 3afa03f33a36..000000000000
--- a/include/asm-x86/device_64.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#ifndef _ASM_X86_64_DEVICE_H
-#define _ASM_X86_64_DEVICE_H
-
-struct dev_archdata {
-#ifdef CONFIG_ACPI
-        void    *acpi_handle;
-#endif
-};
-
-#endif /* _ASM_X86_64_DEVICE_H */
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
index c9e4e8ebc270..8e2b0e6aa8e7 100644
--- a/include/asm-x86/dmi.h
+++ b/include/asm-x86/dmi.h
@@ -1,5 +1,35 @@
+#ifndef _ASM_X86_DMI_H
+#define _ASM_X86_DMI_H
+
+#include <asm/io.h>
+
 #ifdef CONFIG_X86_32
-# include "dmi_32.h"
-#else
-# include "dmi_64.h"
+
+/* Use early IO mappings for DMI because it's initialized early */
+#define dmi_ioremap bt_ioremap
+#define dmi_iounmap bt_iounmap
+#define dmi_alloc alloc_bootmem
+
+#else /* CONFIG_X86_32 */
+
+#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
+
 #endif
diff --git a/include/asm-x86/dmi_32.h b/include/asm-x86/dmi_32.h
deleted file mode 100644
index 38d4eeb7fc7e..000000000000
--- a/include/asm-x86/dmi_32.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_DMI_H
-#define _ASM_DMI_H 1
-
-#include <asm/io.h>
-
-/* Use early IO mappings for DMI because it's initialized early */
-#define dmi_ioremap bt_ioremap
-#define dmi_iounmap bt_iounmap
-#define dmi_alloc alloc_bootmem
-
-#endif
diff --git a/include/asm-x86/dmi_64.h b/include/asm-x86/dmi_64.h
deleted file mode 100644
index d02e32e3c3f0..000000000000
--- a/include/asm-x86/dmi_64.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _ASM_DMI_H
-#define _ASM_DMI_H 1
-
-#include <asm/io.h>
-
-#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/edac.h b/include/asm-x86/edac.h
index f8b888e140b0..cf3200a745ad 100644
--- a/include/asm-x86/edac.h
+++ b/include/asm-x86/edac.h
@@ -1,5 +1,18 @@
-#ifdef CONFIG_X86_32
-# include "edac_32.h"
-#else
-# include "edac_64.h"
+#ifndef _ASM_X86_EDAC_H
+#define _ASM_X86_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+        u32 i, *virt_addr = va;
+
+        /*
+         * Very carefully read and write to memory atomically so we
+         * are interrupt, DMA and SMP safe.
+         */
+        for (i = 0; i < size / 4; i++, virt_addr++)
+                __asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
 #endif
diff --git a/include/asm-x86/edac_32.h b/include/asm-x86/edac_32.h
deleted file mode 100644
index 3e7dd0ab68ce..000000000000
--- a/include/asm-x86/edac_32.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_EDAC_H
-#define ASM_EDAC_H
-
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static __inline__ void atomic_scrub(void *va, u32 size)
-{
-        unsigned long *virt_addr = va;
-        u32 i;
-
-        for (i = 0; i < size / 4; i++, virt_addr++)
-                /* Very carefully read and write to memory atomically
-                 * so we are interrupt, DMA and SMP safe.
-                 */
-                __asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
-}
-
-#endif
diff --git a/include/asm-x86/edac_64.h b/include/asm-x86/edac_64.h
deleted file mode 100644
index cad1cd42b4ee..000000000000
--- a/include/asm-x86/edac_64.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_EDAC_H
-#define ASM_EDAC_H
-
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static __inline__ void atomic_scrub(void *va, u32 size)
-{
-        unsigned int *virt_addr = va;
-        u32 i;
-
-        for (i = 0; i < size / 4; i++, virt_addr++)
-                /* Very carefully read and write to memory atomically
-                 * so we are interrupt, DMA and SMP safe.
-                 */
-                __asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
-}
-
-#endif
diff --git a/include/asm-x86/errno.h b/include/asm-x86/errno.h
index 9d511be8e573..4c82b503d92f 100644
--- a/include/asm-x86/errno.h
+++ b/include/asm-x86/errno.h
@@ -1,13 +1 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "errno_32.h"
-# else
-#  include "errno_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "errno_32.h"
-# else
-#  include "errno_64.h"
-# endif
-#endif
+#include <asm-generic/errno.h>
diff --git a/include/asm-x86/errno_32.h b/include/asm-x86/errno_32.h
deleted file mode 100644
index 969b34374728..000000000000
--- a/include/asm-x86/errno_32.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _I386_ERRNO_H
-#define _I386_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif
diff --git a/include/asm-x86/errno_64.h b/include/asm-x86/errno_64.h
deleted file mode 100644
index 311182129e32..000000000000
--- a/include/asm-x86/errno_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _X8664_ERRNO_H
-#define _X8664_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif
diff --git a/include/asm-x86/fb.h b/include/asm-x86/fb.h
index 238c7ca45877..53018464aea6 100644
--- a/include/asm-x86/fb.h
+++ b/include/asm-x86/fb.h
@@ -1,5 +1,21 @@
+#ifndef _ASM_X86_FB_H
+#define _ASM_X86_FB_H
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+                                unsigned long off)
+{
+        if (boot_cpu_data.x86 > 3)
+                pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+}
+
 #ifdef CONFIG_X86_32
-# include "fb_32.h"
+extern int fb_is_primary_device(struct fb_info *info);
 #else
-# include "fb_64.h"
+static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
 #endif
+
+#endif /* _ASM_X86_FB_H */
diff --git a/include/asm-x86/fb_32.h b/include/asm-x86/fb_32.h
deleted file mode 100644
index d1c6297d4a61..000000000000
--- a/include/asm-x86/fb_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-extern int fb_is_primary_device(struct fb_info *info);
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-                                unsigned long off)
-{
-        if (boot_cpu_data.x86 > 3)
-                pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/include/asm-x86/fb_64.h b/include/asm-x86/fb_64.h
deleted file mode 100644
index 60548e651d12..000000000000
--- a/include/asm-x86/fb_64.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-                                unsigned long off)
-{
-        if (boot_cpu_data.x86 > 3)
-                pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
-}
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-        return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/include/asm-x86/floppy.h b/include/asm-x86/floppy.h
index aecbb6dca21d..a48d7153c097 100644
--- a/include/asm-x86/floppy.h
+++ b/include/asm-x86/floppy.h
@@ -1,5 +1,278 @@
-#ifdef CONFIG_X86_32
-# include "floppy_32.h"
-#else
-# include "floppy_64.h"
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef _ASM_X86_FLOPPY_H
+#define _ASM_X86_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port)            inb_p(port)
+#define fd_outb(value,port)     outb_p(value,port)
+
+#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
+#define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size)  SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id)
+{
+        register unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+        static int calls=0;
+        static int bytes=0;
+        static int dma_wait=0;
 #endif
+        if (!doing_pdma)
+                return floppy_interrupt(irq, dev_id);
+
+#ifdef TRACE_FLPY_INT
+        if(!calls)
+                bytes = virtual_dma_count;
+#endif
+
+        {
+                register int lcount;
+                register char *lptr;
+
+                st = 1;
+                for(lcount=virtual_dma_count, lptr=virtual_dma_addr;
+                    lcount; lcount--, lptr++) {
+                        st=inb(virtual_dma_port+4) & 0xa0 ;
+                        if(st != 0xa0)
+                                break;
+                        if(virtual_dma_mode)
+                                outb_p(*lptr, virtual_dma_port+5);
+                        else
+                                *lptr = inb_p(virtual_dma_port+5);
+                }
+                virtual_dma_count = lcount;
+                virtual_dma_addr = lptr;
+                st = inb(virtual_dma_port+4);
+        }
+
+#ifdef TRACE_FLPY_INT
+        calls++;
+#endif
+        if(st == 0x20)
+                return IRQ_HANDLED;
+        if(!(st & 0x20)) {
+                virtual_dma_residue += virtual_dma_count;
+                virtual_dma_count=0;
+#ifdef TRACE_FLPY_INT
+                printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+                       virtual_dma_count, virtual_dma_residue, calls, bytes,
+                       dma_wait);
+                calls = 0;
+                dma_wait=0;
+#endif
+                doing_pdma = 0;
+                floppy_interrupt(irq, dev_id);
+                return IRQ_HANDLED;
+        }
+#ifdef TRACE_FLPY_INT
+        if(!virtual_dma_count)
+                dma_wait++;
+#endif
+        return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+        if(! (can_use_virtual_dma & 1))
+                disable_dma(FLOPPY_DMA);
+        doing_pdma = 0;
+        virtual_dma_residue += virtual_dma_count;
+        virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+        return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+        return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+        if(can_use_virtual_dma)
+                return request_irq(FLOPPY_IRQ, floppy_hardint,
+                                   IRQF_DISABLED, "floppy", NULL);
+        else
+                return request_irq(FLOPPY_IRQ, floppy_interrupt,
+                                   IRQF_DISABLED, "floppy", NULL);
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+        return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY,get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+        return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+        if((unsigned long) addr >= (unsigned long) high_memory)
+                vfree((void *)addr);
+        else
+                free_pages(addr, get_order(size));
+}
+
+#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size)
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+        if(can_use_virtual_dma == 2) {
+                if((unsigned long) addr >= (unsigned long) high_memory ||
+                   isa_virt_to_bus(addr) >= 0x1000000 ||
+                   _CROSS_64KB(addr, size, 0))
+                        use_virtual_dma = 1;
+                else
+                        use_virtual_dma = 0;
+        } else {
+                use_virtual_dma = can_use_virtual_dma & 1;
+        }
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+        doing_pdma = 1;
+        virtual_dma_port = io;
+        virtual_dma_mode = (mode  == DMA_MODE_WRITE);
+        virtual_dma_addr = addr;
+        virtual_dma_count = size;
+        virtual_dma_residue = 0;
+        return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+        if (CROSS_64KB(addr, size)) {
+                printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+                return -1;
+        }
+#endif
+        /* actual, physical DMA */
+        doing_pdma = 0;
+        clear_dma_ff(FLOPPY_DMA);
+        set_dma_mode(FLOPPY_DMA,mode);
+        set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr));
+        set_dma_count(FLOPPY_DMA,size);
+        enable_dma(FLOPPY_DMA);
+        return 0;
+}
+
+static struct fd_routine_l {
+        int (*_request_dma)(unsigned int dmanr, const char * device_id);
+        void (*_free_dma)(unsigned int dmanr);
+        int (*_get_dma_residue)(unsigned int dummy);
+        unsigned long (*_dma_mem_alloc) (unsigned long size);
+        int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+        {
+                request_dma,
+                free_dma,
+                get_dma_residue,
+                dma_mem_alloc,
+                hard_dma_setup
+        },
+        {
+                vdma_request_dma,
+                vdma_nop,
+                vdma_get_dma_residue,
+                vdma_mem_alloc,
+                vdma_dma_setup
+        }
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user.                Paul G.
+ */
+#define FLOPPY0_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = (CMOS_READ(0x10) >> 4) & 15;              \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define FLOPPY1_TYPE    ({                              \
+        unsigned long flags;                            \
+        unsigned char val;                              \
+        spin_lock_irqsave(&rtc_lock, flags);            \
+        val = CMOS_READ(0x10) & 15;                     \
+        spin_unlock_irqrestore(&rtc_lock, flags);       \
+        val;                                            \
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* _ASM_X86_FLOPPY_H */
diff --git a/include/asm-x86/floppy_32.h b/include/asm-x86/floppy_32.h
deleted file mode 100644
index 99583b39d216..000000000000
--- a/include/asm-x86/floppy_32.h
+++ /dev/null
@@ -1,280 +0,0 @@
-/*
- * Architecture specific parts of the Floppy driver
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1995
- */
-#ifndef __ASM_I386_FLOPPY_H
-#define __ASM_I386_FLOPPY_H
-
-#include <linux/vmalloc.h>
-
-
-/*
- * The DMA channel used by the floppy controller cannot access data at
- * addresses >= 16MB
- *
- * Went back to the 1MB limit, as some people had problems with the floppy
- * driver otherwise. It doesn't matter much for performance anyway, as most
- * floppy accesses go through the track buffer.
- */
-#define _CROSS_64KB(a,s,vdma) \
-(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
-
-#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
-
-
-#define SW fd_routine[use_virtual_dma&1]
-#define CSW fd_routine[can_use_virtual_dma & 1]
-
-
-#define fd_inb(port)                    inb_p(port)
-#define fd_outb(value,port)             outb_p(value,port)
-
-#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
-#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
-#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
-#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
-#define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
-#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
-#define fd_dma_mem_alloc(size)  SW._dma_mem_alloc(size)
-#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
-
-#define FLOPPY_CAN_FALLBACK_ON_NODMA
-
-static int virtual_dma_count;
-static int virtual_dma_residue;
-static char *virtual_dma_addr;
-static int virtual_dma_mode;
-static int doing_pdma;
-
-static irqreturn_t floppy_hardint(int irq, void *dev_id)
-{
-        register unsigned char st;
-
-#undef TRACE_FLPY_INT
-
-#ifdef TRACE_FLPY_INT
-        static int calls=0;
-        static int bytes=0;
-        static int dma_wait=0;
-#endif
-        if (!doing_pdma)
-                return floppy_interrupt(irq, dev_id);
-
-#ifdef TRACE_FLPY_INT
-        if(!calls)
-                bytes = virtual_dma_count;
-#endif
-
-        {
-                register int lcount;
-                register char *lptr;
-
-                st = 1;
-                for(lcount=virtual_dma_count, lptr=virtual_dma_addr; 
-                    lcount; lcount--, lptr++) {
-                        st=inb(virtual_dma_port+4) & 0xa0 ;
-                        if(st != 0xa0) 
-                                break;
-                        if(virtual_dma_mode)
-                                outb_p(*lptr, virtual_dma_port+5);
-                        else
-                                *lptr = inb_p(virtual_dma_port+5);
-                }
-                virtual_dma_count = lcount;
-                virtual_dma_addr = lptr;
-                st = inb(virtual_dma_port+4);
-        }
-
-#ifdef TRACE_FLPY_INT
-        calls++;
-#endif
-        if(st == 0x20)
-                return IRQ_HANDLED;
-        if(!(st & 0x20)) {
-                virtual_dma_residue += virtual_dma_count;
-                virtual_dma_count=0;
-#ifdef TRACE_FLPY_INT
-                printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
-                       virtual_dma_count, virtual_dma_residue, calls, bytes,
-                       dma_wait);
-                calls = 0;
-                dma_wait=0;
-#endif
-                doing_pdma = 0;
-                floppy_interrupt(irq, dev_id);
-                return IRQ_HANDLED;
-        }
-#ifdef TRACE_FLPY_INT
-        if(!virtual_dma_count)
-                dma_wait++;
-#endif
-        return IRQ_HANDLED;
-}
-
-static void fd_disable_dma(void)
-{
-        if(! (can_use_virtual_dma & 1))
-                disable_dma(FLOPPY_DMA);
-        doing_pdma = 0;
-        virtual_dma_residue += virtual_dma_count;
-        virtual_dma_count=0;
-}
-
-static int vdma_request_dma(unsigned int dmanr, const char * device_id)
-{
-        return 0;
-}
-
-static void vdma_nop(unsigned int dummy)
-{
-}
-
-
-static int vdma_get_dma_residue(unsigned int dummy)
-{
-        return virtual_dma_count + virtual_dma_residue;
-}
-
-
-static int fd_request_irq(void)
-{
-        if(can_use_virtual_dma)
-                return request_irq(FLOPPY_IRQ, floppy_hardint,
-                                   IRQF_DISABLED, "floppy", NULL);
-        else
-                return request_irq(FLOPPY_IRQ, floppy_interrupt,
-                                   IRQF_DISABLED, "floppy", NULL);
-
-}
-
-static unsigned long dma_mem_alloc(unsigned long size)
-{
-        return __get_dma_pages(GFP_KERNEL,get_order(size));
-}
-
-
-static unsigned long vdma_mem_alloc(unsigned long size)
-{
-        return (unsigned long) vmalloc(size);
-
-}
-
-#define nodma_mem_alloc(size) vdma_mem_alloc(size)
-
-static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
-{
-        if((unsigned int) addr >= (unsigned int) high_memory)
-                vfree((void *)addr);
-        else
-                free_pages(addr, get_order(size));              
-}
-
-#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
-
-static void _fd_chose_dma_mode(char *addr, unsigned long size)
-{
-        if(can_use_virtual_dma == 2) {
-                if((unsigned int) addr >= (unsigned int) high_memory ||
-                   isa_virt_to_bus(addr) >= 0x1000000 ||
-                   _CROSS_64KB(addr, size, 0))
-                        use_virtual_dma = 1;
-                else
-                        use_virtual_dma = 0;
-        } else {
-                use_virtual_dma = can_use_virtual_dma & 1;
-        }
-}
-
-#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
-
-
-static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-        doing_pdma = 1;
-        virtual_dma_port = io;
-        virtual_dma_mode = (mode  == DMA_MODE_WRITE);
-        virtual_dma_addr = addr;
-        virtual_dma_count = size;
-        virtual_dma_residue = 0;
-        return 0;
-}
-
-static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-#ifdef FLOPPY_SANITY_CHECK
-        if (CROSS_64KB(addr, size)) {
-                printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
-                return -1;
-        }
-#endif
-        /* actual, physical DMA */
-        doing_pdma = 0;
-        clear_dma_ff(FLOPPY_DMA);
-        set_dma_mode(FLOPPY_DMA,mode);
-        set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr));
-        set_dma_count(FLOPPY_DMA,size);
-        enable_dma(FLOPPY_DMA);
-        return 0;
-}
-
-static struct fd_routine_l {
-        int (*_request_dma)(unsigned int dmanr, const char * device_id);
-        void (*_free_dma)(unsigned int dmanr);
-        int (*_get_dma_residue)(unsigned int dummy);
-        unsigned long (*_dma_mem_alloc) (unsigned long size);
-        int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
-} fd_routine[] = {
-        {
-                request_dma,
-                free_dma,
-                get_dma_residue,
-                dma_mem_alloc,
-                hard_dma_setup
-        },
-        {
-                vdma_request_dma,
-                vdma_nop,
-                vdma_get_dma_residue,
-                vdma_mem_alloc,
-                vdma_dma_setup
-        }
-};
-
-
-static int FDC1 = 0x3f0;
-static int FDC2 = -1;
-
-/*
- * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
- * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
- * coincides with another rtc CMOS user.                Paul G.
- */
-#define FLOPPY0_TYPE    ({                              \
-        unsigned long flags;                            \
-        unsigned char val;                              \
-        spin_lock_irqsave(&rtc_lock, flags);            \
-        val = (CMOS_READ(0x10) >> 4) & 15;              \
-        spin_unlock_irqrestore(&rtc_lock, flags);       \
-        val;                                            \
-})
-
-#define FLOPPY1_TYPE    ({                              \
-        unsigned long flags;                            \
-        unsigned char val;                              \
-        spin_lock_irqsave(&rtc_lock, flags);            \
-        val = CMOS_READ(0x10) & 15;                     \
-        spin_unlock_irqrestore(&rtc_lock, flags);       \
-        val;                                            \
-})
-
-#define N_FDC 2
-#define N_DRIVE 8
-
-#define EXTRA_FLOPPY_PARAMS
-
-#endif /* __ASM_I386_FLOPPY_H */
diff --git a/include/asm-x86/floppy_64.h b/include/asm-x86/floppy_64.h
deleted file mode 100644
index d993380dcb47..000000000000
--- a/include/asm-x86/floppy_64.h
+++ /dev/null
@@ -1,279 +0,0 @@
-/*
- * Architecture specific parts of the Floppy driver
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1995
- */
-#ifndef __ASM_X86_64_FLOPPY_H
-#define __ASM_X86_64_FLOPPY_H
-
-#include <linux/vmalloc.h>
-
-
-/*
- * The DMA channel used by the floppy controller cannot access data at
- * addresses >= 16MB
- *
- * Went back to the 1MB limit, as some people had problems with the floppy
- * driver otherwise. It doesn't matter much for performance anyway, as most
- * floppy accesses go through the track buffer.
- */
-#define _CROSS_64KB(a,s,vdma) \
-(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
-
-#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
-
-
-#define SW fd_routine[use_virtual_dma&1]
-#define CSW fd_routine[can_use_virtual_dma & 1]
-
-
-#define fd_inb(port)                    inb_p(port)
-#define fd_outb(value,port)             outb_p(value,port)
-
-#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
-#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
-#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
-#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
-#define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
-#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
-#define fd_dma_mem_alloc(size)  SW._dma_mem_alloc(size)
-#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
-
-#define FLOPPY_CAN_FALLBACK_ON_NODMA
-
-static int virtual_dma_count;
-static int virtual_dma_residue;
-static char *virtual_dma_addr;
-static int virtual_dma_mode;
-static int doing_pdma;
-
-static irqreturn_t floppy_hardint(int irq, void *dev_id)
-{
-        register unsigned char st;
-
-#undef TRACE_FLPY_INT
-
-#ifdef TRACE_FLPY_INT
-        static int calls=0;
-        static int bytes=0;
-        static int dma_wait=0;
-#endif
-        if (!doing_pdma)
-                return floppy_interrupt(irq, dev_id);
-
-#ifdef TRACE_FLPY_INT
-        if(!calls)
-                bytes = virtual_dma_count;
-#endif
-
-        {
-                register int lcount;
-                register char *lptr;
-
-                st = 1;
-                for(lcount=virtual_dma_count, lptr=virtual_dma_addr; 
-                    lcount; lcount--, lptr++) {
-                        st=inb(virtual_dma_port+4) & 0xa0 ;
-                        if(st != 0xa0) 
-                                break;
-                        if(virtual_dma_mode)
-                                outb_p(*lptr, virtual_dma_port+5);
-                        else
-                                *lptr = inb_p(virtual_dma_port+5);
-                }
-                virtual_dma_count = lcount;
-                virtual_dma_addr = lptr;
-                st = inb(virtual_dma_port+4);
-        }
-
-#ifdef TRACE_FLPY_INT
-        calls++;
-#endif
-        if(st == 0x20)
-                return IRQ_HANDLED;
-        if(!(st & 0x20)) {
-                virtual_dma_residue += virtual_dma_count;
-                virtual_dma_count=0;
-#ifdef TRACE_FLPY_INT
-                printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
-                       virtual_dma_count, virtual_dma_residue, calls, bytes,
-                       dma_wait);
-                calls = 0;
-                dma_wait=0;
-#endif
-                doing_pdma = 0;
-                floppy_interrupt(irq, dev_id);
-                return IRQ_HANDLED;
-        }
-#ifdef TRACE_FLPY_INT
-        if(!virtual_dma_count)
-                dma_wait++;
-#endif
-        return IRQ_HANDLED;
-}
-
-static void fd_disable_dma(void)
-{
-        if(! (can_use_virtual_dma & 1))
-                disable_dma(FLOPPY_DMA);
-        doing_pdma = 0;
-        virtual_dma_residue += virtual_dma_count;
-        virtual_dma_count=0;
-}
-
-static int vdma_request_dma(unsigned int dmanr, const char * device_id)
-{
-        return 0;
-}
-
-static void vdma_nop(unsigned int dummy)
-{
-}
-
-
-static int vdma_get_dma_residue(unsigned int dummy)
-{
-        return virtual_dma_count + virtual_dma_residue;
-}
-
-
-static int fd_request_irq(void)
-{
-        if(can_use_virtual_dma)
-                return request_irq(FLOPPY_IRQ, floppy_hardint,
-                                   IRQF_DISABLED, "floppy", NULL);
-        else
-                return request_irq(FLOPPY_IRQ, floppy_interrupt,
-                                   IRQF_DISABLED, "floppy", NULL);
-}
-
-static unsigned long dma_mem_alloc(unsigned long size)
-{
-        return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY,get_order(size));
-}
-
-
-static unsigned long vdma_mem_alloc(unsigned long size)
-{
-        return (unsigned long) vmalloc(size);
-
-}
-
-#define nodma_mem_alloc(size) vdma_mem_alloc(size)
-
-static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
-{
-        if((unsigned long) addr >= (unsigned long) high_memory)
-                vfree((void *)addr);
-        else
-                free_pages(addr, get_order(size));              
-}
-
-#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
-
-static void _fd_chose_dma_mode(char *addr, unsigned long size)
-{
-        if(can_use_virtual_dma == 2) {
-                if((unsigned long) addr >= (unsigned long) high_memory ||
-                   isa_virt_to_bus(addr) >= 0x1000000 ||
-                   _CROSS_64KB(addr, size, 0))
-                        use_virtual_dma = 1;
-                else
-                        use_virtual_dma = 0;
-        } else {
-                use_virtual_dma = can_use_virtual_dma & 1;
-        }
-}
-
-#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
-
-
-static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-        doing_pdma = 1;
-        virtual_dma_port = io;
-        virtual_dma_mode = (mode  == DMA_MODE_WRITE);
-        virtual_dma_addr = addr;
-        virtual_dma_count = size;
-        virtual_dma_residue = 0;
-        return 0;
-}
-
-static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-#ifdef FLOPPY_SANITY_CHECK
-        if (CROSS_64KB(addr, size)) {
-                printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
-                return -1;
-        }
-#endif
-        /* actual, physical DMA */
-        doing_pdma = 0;
-        clear_dma_ff(FLOPPY_DMA);
-        set_dma_mode(FLOPPY_DMA,mode);
-        set_dma_addr(FLOPPY_DMA,isa_virt_to_bus(addr));
-        set_dma_count(FLOPPY_DMA,size);
-        enable_dma(FLOPPY_DMA);
-        return 0;
-}
-
-static struct fd_routine_l {
-        int (*_request_dma)(unsigned int dmanr, const char * device_id);
-        void (*_free_dma)(unsigned int dmanr);
-        int (*_get_dma_residue)(unsigned int dummy);
-        unsigned long (*_dma_mem_alloc) (unsigned long size);
-        int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
-} fd_routine[] = {
-        {
-                request_dma,
-                free_dma,
-                get_dma_residue,
-                dma_mem_alloc,
-                hard_dma_setup
-        },
-        {
-                vdma_request_dma,
-                vdma_nop,
-                vdma_get_dma_residue,
-                vdma_mem_alloc,
-                vdma_dma_setup
-        }
-};
-
-
-static int FDC1 = 0x3f0;
-static int FDC2 = -1;
-
-/*
- * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
- * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
- * coincides with another rtc CMOS user.                Paul G.
- */
-#define FLOPPY0_TYPE    ({                              \
-        unsigned long flags;                            \
-        unsigned char val;                              \
-        spin_lock_irqsave(&rtc_lock, flags);            \
-        val = (CMOS_READ(0x10) >> 4) & 15;              \
-        spin_unlock_irqrestore(&rtc_lock, flags);       \
-        val;                                            \
-})
-
-#define FLOPPY1_TYPE    ({                              \
-        unsigned long flags;                            \
-        unsigned char val;                              \
-        spin_lock_irqsave(&rtc_lock, flags);            \
-        val = CMOS_READ(0x10) & 15;                     \
-        spin_unlock_irqrestore(&rtc_lock, flags);       \
-        val;                                            \
-})
-
-#define N_FDC 2
-#define N_DRIVE 8
-
-#define EXTRA_FLOPPY_PARAMS
-
-#endif /* __ASM_X86_64_FLOPPY_H */
diff --git a/include/asm-x86/frame.i b/include/asm-x86/frame.h
index 03620251ae17..06850a7194e1 100644
--- a/include/asm-x86/frame.i
+++ b/include/asm-x86/frame.h
@@ -1,3 +1,5 @@
+#ifdef __ASSEMBLY__
+
 #include <asm/dwarf2.h>
 
 /* The annotation hides the frame from the unwinder and makes it look
@@ -21,3 +23,5 @@
         .macro ENDFRAME
         .endm
 #endif
+
+#endif  /*  __ASSEMBLY__  */
diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
index 34649585bb59..4f85f0f4b563 100644
--- a/include/asm-x86/hardirq_32.h
+++ b/include/asm-x86/hardirq_32.h
@@ -10,10 +10,14 @@ typedef struct {
         unsigned int __nmi_count;       /* arch dependent */
         unsigned int apic_timer_irqs;   /* arch dependent */
         unsigned int irq0_irqs;
+        unsigned int irq_resched_count;
+        unsigned int irq_call_count;
+        unsigned int irq_tlb_count;
+        unsigned int irq_thermal_count;
+        unsigned int irq_spurious_count;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
-extern irq_cpustat_t irq_stat[];
 
 #define __ARCH_IRQ_STAT
 #define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
diff --git a/include/asm-x86/hw_irq_64.h b/include/asm-x86/hw_irq_64.h
index 09dfc18a6dd0..a470d59da678 100644
--- a/include/asm-x86/hw_irq_64.h
+++ b/include/asm-x86/hw_irq_64.h
@@ -40,22 +40,22 @@
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
  */
-#define IRQ0_VECTOR             FIRST_EXTERNAL_VECTOR + 0x10
-#define IRQ1_VECTOR             IRQ0_VECTOR + 1
-#define IRQ2_VECTOR             IRQ0_VECTOR + 2
-#define IRQ3_VECTOR             IRQ0_VECTOR + 3
-#define IRQ4_VECTOR             IRQ0_VECTOR + 4
-#define IRQ5_VECTOR             IRQ0_VECTOR + 5 
-#define IRQ6_VECTOR             IRQ0_VECTOR + 6
-#define IRQ7_VECTOR             IRQ0_VECTOR + 7
-#define IRQ8_VECTOR             IRQ0_VECTOR + 8
-#define IRQ9_VECTOR             IRQ0_VECTOR + 9
-#define IRQ10_VECTOR            IRQ0_VECTOR + 10
-#define IRQ11_VECTOR            IRQ0_VECTOR + 11
-#define IRQ12_VECTOR            IRQ0_VECTOR + 12
-#define IRQ13_VECTOR            IRQ0_VECTOR + 13
-#define IRQ14_VECTOR            IRQ0_VECTOR + 14
-#define IRQ15_VECTOR            IRQ0_VECTOR + 15
+#define IRQ0_VECTOR             (FIRST_EXTERNAL_VECTOR + 0x10)
+#define IRQ1_VECTOR             (IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR             (IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR             (IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR             (IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR             (IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR             (IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR             (IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR             (IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR             (IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR            (IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR            (IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR            (IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR            (IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR            (IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR            (IRQ0_VECTOR + 15)
 
 /*
  * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -148,9 +148,6 @@ extern atomic_t irq_mis_count;
 
 #define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
 
-#define __STR(x) #x
-#define STR(x) __STR(x)
-
 #include <asm/ptrace.h>
 
 #define IRQ_NAME2(nr) nr##_interrupt(void)
diff --git a/include/asm-x86/intel_arch_perfmon.h b/include/asm-x86/intel_arch_perfmon.h
index 4f6d4e6bf57e..fa0fd068bc2e 100644
--- a/include/asm-x86/intel_arch_perfmon.h
+++ b/include/asm-x86/intel_arch_perfmon.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "intel_arch_perfmon_32.h"
-#else
-# include "intel_arch_perfmon_64.h"
-#endif
+#ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
+#define _ASM_X86_INTEL_ARCH_PERFMON_H
+
+#define MSR_ARCH_PERFMON_PERFCTR0               0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1               0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0              0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1              0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE   (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT       (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS        (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR       (1 << 16)
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL   (0x3c)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+        (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+union cpuid10_eax {
+        struct {
+                unsigned int version_id:8;
+                unsigned int num_counters:8;
+                unsigned int bit_width:8;
+                unsigned int mask_length:8;
+        } split;
+        unsigned int full;
+};
+
+#endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/intel_arch_perfmon_32.h b/include/asm-x86/intel_arch_perfmon_32.h
deleted file mode 100644
index b52cd60a075b..000000000000
--- a/include/asm-x86/intel_arch_perfmon_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef X86_INTEL_ARCH_PERFMON_H
-#define X86_INTEL_ARCH_PERFMON_H 1
-
-#define MSR_ARCH_PERFMON_PERFCTR0               0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1               0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0              0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1              0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL   (0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-                                (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-
-union cpuid10_eax {
-        struct {
-                unsigned int version_id:8;
-                unsigned int num_counters:8;
-                unsigned int bit_width:8;
-                unsigned int mask_length:8;
-        } split;
-        unsigned int full;
-};
-
-#endif  /* X86_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/intel_arch_perfmon_64.h b/include/asm-x86/intel_arch_perfmon_64.h
deleted file mode 100644
index 8633331420ec..000000000000
--- a/include/asm-x86/intel_arch_perfmon_64.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef X86_64_INTEL_ARCH_PERFMON_H
-#define X86_64_INTEL_ARCH_PERFMON_H 1
-
-#define MSR_ARCH_PERFMON_PERFCTR0               0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1               0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0              0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1              0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL   (0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-                                (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-
-union cpuid10_eax {
-        struct {
-                unsigned int version_id:8;
-                unsigned int num_counters:8;
-                unsigned int bit_width:8;
-                unsigned int mask_length:8;
-        } split;
-        unsigned int full;
-};
-
-#endif  /* X86_64_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
index 4ea7b1ad3c1d..fe881cd1e6f4 100644
--- a/include/asm-x86/io_32.h
+++ b/include/asm-x86/io_32.h
@@ -199,17 +199,22 @@ static inline void writel(unsigned int b, volatile void __iomem *addr)
 
 #define mmiowb()
 
-static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count)
+static inline void
+memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {
-        memset((void __force *) addr, val, count);
+        memset((void __force *)addr, val, count);
 }
-static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
+
+static inline void
+memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
 {
-        __memcpy(dst, (void __force *) src, count);
+        __memcpy(dst, (const void __force *)src, count);
 }
-static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count)
+
+static inline void
+memcpy_toio(volatile void __iomem *dst, const void *src, int count)
 {
-        __memcpy((void __force *) dst, src, count);
+        __memcpy((void __force *)dst, src, count);
 }
 
 /*
diff --git a/include/asm-x86/ioctls.h b/include/asm-x86/ioctls.h
index 1e0fd48f18bc..93c894dc5154 100644
--- a/include/asm-x86/ioctls.h
+++ b/include/asm-x86/ioctls.h
@@ -1,13 +1,87 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "ioctls_32.h"
-# else
-#  include "ioctls_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "ioctls_32.h"
-# else
-#  include "ioctls_64.h"
-# endif
+#ifndef _ASM_X86_IOCTLS_H
+#define _ASM_X86_IOCTLS_H
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS          0x5401
+#define TCSETS          0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
+#define TCSETSW         0x5403
+#define TCSETSF         0x5404
+#define TCGETA          0x5405
+#define TCSETA          0x5406
+#define TCSETAW         0x5407
+#define TCSETAF         0x5408
+#define TCSBRK          0x5409
+#define TCXONC          0x540A
+#define TCFLSH          0x540B
+#define TIOCEXCL        0x540C
+#define TIOCNXCL        0x540D
+#define TIOCSCTTY       0x540E
+#define TIOCGPGRP       0x540F
+#define TIOCSPGRP       0x5410
+#define TIOCOUTQ        0x5411
+#define TIOCSTI         0x5412
+#define TIOCGWINSZ      0x5413
+#define TIOCSWINSZ      0x5414
+#define TIOCMGET        0x5415
+#define TIOCMBIS        0x5416
+#define TIOCMBIC        0x5417
+#define TIOCMSET        0x5418
+#define TIOCGSOFTCAR    0x5419
+#define TIOCSSOFTCAR    0x541A
+#define FIONREAD        0x541B
+#define TIOCINQ         FIONREAD
+#define TIOCLINUX       0x541C
+#define TIOCCONS        0x541D
+#define TIOCGSERIAL     0x541E
+#define TIOCSSERIAL     0x541F
+#define TIOCPKT         0x5420
+#define FIONBIO         0x5421
+#define TIOCNOTTY       0x5422
+#define TIOCSETD        0x5423
+#define TIOCGETD        0x5424
+#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
+/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
+#define TIOCSBRK        0x5427  /* BSD compatibility */
+#define TIOCCBRK        0x5428  /* BSD compatibility */
+#define TIOCGSID        0x5429  /* Return the session ID of FD */
+#define TCGETS2         _IOR('T',0x2A, struct termios2)
+#define TCSETS2         _IOW('T',0x2B, struct termios2)
+#define TCSETSW2        _IOW('T',0x2C, struct termios2)
+#define TCSETSF2        _IOW('T',0x2D, struct termios2)
+#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
+
+#define FIONCLEX        0x5450
+#define FIOCLEX         0x5451
+#define FIOASYNC        0x5452
+#define TIOCSERCONFIG   0x5453
+#define TIOCSERGWILD    0x5454
+#define TIOCSERSWILD    0x5455
+#define TIOCGLCKTRMIOS  0x5456
+#define TIOCSLCKTRMIOS  0x5457
+#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
+#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
+#define FIOQSIZE        0x5460
+
+/* Used for packet mode */
+#define TIOCPKT_DATA             0
+#define TIOCPKT_FLUSHREAD        1
+#define TIOCPKT_FLUSHWRITE       2
+#define TIOCPKT_STOP             4
+#define TIOCPKT_START            8
+#define TIOCPKT_NOSTOP          16
+#define TIOCPKT_DOSTOP          32
+
+#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
+
 #endif
diff --git a/include/asm-x86/ioctls_32.h b/include/asm-x86/ioctls_32.h
deleted file mode 100644
index ef5878762dc9..000000000000
--- a/include/asm-x86/ioctls_32.h
+++ /dev/null
@@ -1,87 +0,0 @@
-#ifndef __ARCH_I386_IOCTLS_H__
-#define __ARCH_I386_IOCTLS_H__
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS          0x5401
-#define TCSETS          0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
-#define TCSETSW         0x5403
-#define TCSETSF         0x5404
-#define TCGETA          0x5405
-#define TCSETA          0x5406
-#define TCSETAW         0x5407
-#define TCSETAF         0x5408
-#define TCSBRK          0x5409
-#define TCXONC          0x540A
-#define TCFLSH          0x540B
-#define TIOCEXCL        0x540C
-#define TIOCNXCL        0x540D
-#define TIOCSCTTY       0x540E
-#define TIOCGPGRP       0x540F
-#define TIOCSPGRP       0x5410
-#define TIOCOUTQ        0x5411
-#define TIOCSTI         0x5412
-#define TIOCGWINSZ      0x5413
-#define TIOCSWINSZ      0x5414
-#define TIOCMGET        0x5415
-#define TIOCMBIS        0x5416
-#define TIOCMBIC        0x5417
-#define TIOCMSET        0x5418
-#define TIOCGSOFTCAR    0x5419
-#define TIOCSSOFTCAR    0x541A
-#define FIONREAD        0x541B
-#define TIOCINQ         FIONREAD
-#define TIOCLINUX       0x541C
-#define TIOCCONS        0x541D
-#define TIOCGSERIAL     0x541E
-#define TIOCSSERIAL     0x541F
-#define TIOCPKT         0x5420
-#define FIONBIO         0x5421
-#define TIOCNOTTY       0x5422
-#define TIOCSETD        0x5423
-#define TIOCGETD        0x5424
-#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
-/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
-#define TIOCSBRK        0x5427  /* BSD compatibility */
-#define TIOCCBRK        0x5428  /* BSD compatibility */
-#define TIOCGSID        0x5429  /* Return the session ID of FD */
-#define TCGETS2         _IOR('T',0x2A, struct termios2)
-#define TCSETS2         _IOW('T',0x2B, struct termios2)
-#define TCSETSW2        _IOW('T',0x2C, struct termios2)
-#define TCSETSF2        _IOW('T',0x2D, struct termios2)
-#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
-
-#define FIONCLEX        0x5450
-#define FIOCLEX         0x5451
-#define FIOASYNC        0x5452
-#define TIOCSERCONFIG   0x5453
-#define TIOCSERGWILD    0x5454
-#define TIOCSERSWILD    0x5455
-#define TIOCGLCKTRMIOS  0x5456
-#define TIOCSLCKTRMIOS  0x5457
-#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
-#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
-#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
-#define FIOQSIZE        0x5460
-
-/* Used for packet mode */
-#define TIOCPKT_DATA             0
-#define TIOCPKT_FLUSHREAD        1
-#define TIOCPKT_FLUSHWRITE       2
-#define TIOCPKT_STOP             4
-#define TIOCPKT_START            8
-#define TIOCPKT_NOSTOP          16
-#define TIOCPKT_DOSTOP          32
-
-#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
-
-#endif
diff --git a/include/asm-x86/ioctls_64.h b/include/asm-x86/ioctls_64.h
deleted file mode 100644
index 3fc0b15a0d7e..000000000000
--- a/include/asm-x86/ioctls_64.h
+++ /dev/null
@@ -1,86 +0,0 @@
-#ifndef __ARCH_X8664_IOCTLS_H__
-#define __ARCH_X8664_IOCTLS_H__
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS          0x5401
-#define TCSETS          0x5402
-#define TCSETSW         0x5403
-#define TCSETSF         0x5404
-#define TCGETA          0x5405
-#define TCSETA          0x5406
-#define TCSETAW         0x5407
-#define TCSETAF         0x5408
-#define TCSBRK          0x5409
-#define TCXONC          0x540A
-#define TCFLSH          0x540B
-#define TIOCEXCL        0x540C
-#define TIOCNXCL        0x540D
-#define TIOCSCTTY       0x540E
-#define TIOCGPGRP       0x540F
-#define TIOCSPGRP       0x5410
-#define TIOCOUTQ        0x5411
-#define TIOCSTI         0x5412
-#define TIOCGWINSZ      0x5413
-#define TIOCSWINSZ      0x5414
-#define TIOCMGET        0x5415
-#define TIOCMBIS        0x5416
-#define TIOCMBIC        0x5417
-#define TIOCMSET        0x5418
-#define TIOCGSOFTCAR    0x5419
-#define TIOCSSOFTCAR    0x541A
-#define FIONREAD        0x541B
-#define TIOCINQ         FIONREAD
-#define TIOCLINUX       0x541C
-#define TIOCCONS        0x541D
-#define TIOCGSERIAL     0x541E
-#define TIOCSSERIAL     0x541F
-#define TIOCPKT         0x5420
-#define FIONBIO         0x5421
-#define TIOCNOTTY       0x5422
-#define TIOCSETD        0x5423
-#define TIOCGETD        0x5424
-#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
-#define TIOCSBRK        0x5427  /* BSD compatibility */
-#define TIOCCBRK        0x5428  /* BSD compatibility */
-#define TIOCGSID        0x5429  /* Return the session ID of FD */
-#define TCGETS2         _IOR('T',0x2A, struct termios2)
-#define TCSETS2         _IOW('T',0x2B, struct termios2)
-#define TCSETSW2        _IOW('T',0x2C, struct termios2)
-#define TCSETSF2        _IOW('T',0x2D, struct termios2)
-#define TIOCGPTN        _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK      _IOW('T',0x31, int)  /* Lock/unlock Pty */
-
-#define FIONCLEX        0x5450  /* these numbers need to be adjusted. */
-#define FIOCLEX         0x5451
-#define FIOASYNC        0x5452
-#define TIOCSERCONFIG   0x5453
-#define TIOCSERGWILD    0x5454
-#define TIOCSERSWILD    0x5455
-#define TIOCGLCKTRMIOS  0x5456
-#define TIOCSLCKTRMIOS  0x5457
-#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
-#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
-#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
-#define FIOQSIZE       0x5460
-
-/* Used for packet mode */
-#define TIOCPKT_DATA             0
-#define TIOCPKT_FLUSHREAD        1
-#define TIOCPKT_FLUSHWRITE       2
-#define TIOCPKT_STOP             4
-#define TIOCPKT_START            8
-#define TIOCPKT_NOSTOP          16
-#define TIOCPKT_DOSTOP          32
-
-#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
-
-#endif
diff --git a/include/asm-x86/ipcbuf.h b/include/asm-x86/ipcbuf.h
index eb2e448c6e28..2adf8b39a40b 100644
--- a/include/asm-x86/ipcbuf.h
+++ b/include/asm-x86/ipcbuf.h
@@ -1,13 +1,29 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "ipcbuf_32.h"
-# else
-#  include "ipcbuf_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "ipcbuf_32.h"
-# else
-#  include "ipcbuf_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_IPCBUF_H
+#define _ASM_X86_IPCBUF_H
+
+/*
+ * The ipc64_perm structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm
+{
+        __kernel_key_t          key;
+        __kernel_uid32_t        uid;
+        __kernel_gid32_t        gid;
+        __kernel_uid32_t        cuid;
+        __kernel_gid32_t        cgid;
+        __kernel_mode_t         mode;
+        unsigned short          __pad1;
+        unsigned short          seq;
+        unsigned short          __pad2;
+        unsigned long           __unused1;
+        unsigned long           __unused2;
+};
+
+#endif /* _ASM_X86_IPCBUF_H */
diff --git a/include/asm-x86/ipcbuf_32.h b/include/asm-x86/ipcbuf_32.h
deleted file mode 100644
index 0dcad4f84c2a..000000000000
--- a/include/asm-x86/ipcbuf_32.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __i386_IPCBUF_H__
-#define __i386_IPCBUF_H__
-
-/*
- * The ipc64_perm structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 32-bit mode_t and seq
- * - 2 miscellaneous 32-bit values
- */
-
-struct ipc64_perm
-{
-        __kernel_key_t          key;
-        __kernel_uid32_t        uid;
-        __kernel_gid32_t        gid;
-        __kernel_uid32_t        cuid;
-        __kernel_gid32_t        cgid;
-        __kernel_mode_t         mode;
-        unsigned short          __pad1;
-        unsigned short          seq;
-        unsigned short          __pad2;
-        unsigned long           __unused1;
-        unsigned long           __unused2;
-};
-
-#endif /* __i386_IPCBUF_H__ */
diff --git a/include/asm-x86/ipcbuf_64.h b/include/asm-x86/ipcbuf_64.h
deleted file mode 100644
index 470cf85e3ba8..000000000000
--- a/include/asm-x86/ipcbuf_64.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __x86_64_IPCBUF_H__
-#define __x86_64_IPCBUF_H__
-
-/*
- * The ipc64_perm structure for x86_64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 32-bit mode_t and seq
- * - 2 miscellaneous 32-bit values
- */
-
-struct ipc64_perm
-{
-        __kernel_key_t          key;
-        __kernel_uid32_t        uid;
-        __kernel_gid32_t        gid;
-        __kernel_uid32_t        cuid;
-        __kernel_gid32_t        cgid;
-        __kernel_mode_t         mode;
-        unsigned short          __pad1;
-        unsigned short          seq;
-        unsigned short          __pad2;
-        unsigned long           __unused1;
-        unsigned long           __unused2;
-};
-
-#endif /* __x86_64_IPCBUF_H__ */
diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h
index 38479106c259..e2f9b62e535e 100644
--- a/include/asm-x86/kdebug.h
+++ b/include/asm-x86/kdebug.h
@@ -1,5 +1,33 @@
-#ifdef CONFIG_X86_32
-# include "kdebug_32.h"
-#else
-# include "kdebug_64.h"
+#ifndef _ASM_X86_KDEBUG_H
+#define _ASM_X86_KDEBUG_H
+
+#include <linux/notifier.h>
+
+struct pt_regs;
+
+/* Grossly misnamed. */
+enum die_val {
+        DIE_OOPS = 1,
+        DIE_INT3,
+        DIE_DEBUG,
+        DIE_PANIC,
+        DIE_NMI,
+        DIE_DIE,
+        DIE_NMIWATCHDOG,
+        DIE_KERNELDEBUG,
+        DIE_TRAP,
+        DIE_GPF,
+        DIE_CALL,
+        DIE_NMI_IPI,
+        DIE_PAGE_FAULT,
+};
+
+extern void printk_address(unsigned long address);
+extern void die(const char *,struct pt_regs *,long);
+extern void __die(const char *,struct pt_regs *,long);
+extern void show_registers(struct pt_regs *regs);
+extern void dump_pagetable(unsigned long);
+extern unsigned long oops_begin(void);
+extern void oops_end(unsigned long);
+
 #endif
diff --git a/include/asm-x86/kdebug_32.h b/include/asm-x86/kdebug_32.h
deleted file mode 100644
index 181d437eef4b..000000000000
--- a/include/asm-x86/kdebug_32.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _I386_KDEBUG_H
-#define _I386_KDEBUG_H 1
-
-/*
- * Aug-05 2004 Ported by Prasanna S Panchamukhi <prasanna@in.ibm.com>
- * from x86_64 architecture.
- */
-
-struct pt_regs;
-
-/* Grossly misnamed. */
-enum die_val {
-        DIE_OOPS = 1,
-        DIE_INT3,
-        DIE_DEBUG,
-        DIE_PANIC,
-        DIE_NMI,
-        DIE_DIE,
-        DIE_NMIWATCHDOG,
-        DIE_KERNELDEBUG,
-        DIE_TRAP,
-        DIE_GPF,
-        DIE_CALL,
-        DIE_NMI_IPI,
-};
-
-#endif
diff --git a/include/asm-x86/kdebug_64.h b/include/asm-x86/kdebug_64.h
deleted file mode 100644
index df413e05375e..000000000000
--- a/include/asm-x86/kdebug_64.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef _X86_64_KDEBUG_H
-#define _X86_64_KDEBUG_H 1
-
-#include <linux/compiler.h>
-
-struct pt_regs;
-
-/* Grossly misnamed. */
-enum die_val {
-        DIE_OOPS = 1,
-        DIE_INT3,
-        DIE_DEBUG,
-        DIE_PANIC,
-        DIE_NMI,
-        DIE_DIE,
-        DIE_NMIWATCHDOG,
-        DIE_KERNELDEBUG,
-        DIE_TRAP,
-        DIE_GPF,
-        DIE_CALL,
-        DIE_NMI_IPI,
-};
-
-extern void printk_address(unsigned long address);
-extern void die(const char *,struct pt_regs *,long);
-extern void __die(const char *,struct pt_regs *,long);
-extern void show_registers(struct pt_regs *regs);
-extern void dump_pagetable(unsigned long);
-extern unsigned long oops_begin(void);
-extern void oops_end(unsigned long);
-
-#endif
diff --git a/include/asm-x86/kmap_types.h b/include/asm-x86/kmap_types.h
index e4ec724b298e..5f4174132a22 100644
--- a/include/asm-x86/kmap_types.h
+++ b/include/asm-x86/kmap_types.h
@@ -1,5 +1,29 @@
-#ifdef CONFIG_X86_32
-# include "kmap_types_32.h"
+#ifndef _ASM_X86_KMAP_TYPES_H
+#define _ASM_X86_KMAP_TYPES_H
+
+#if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
+# define D(n) __KM_FENCE_##n ,
 #else
-# include "kmap_types_64.h"
+# define D(n)
+#endif
+
+enum km_type {
+D(0)    KM_BOUNCE_READ,
+D(1)    KM_SKB_SUNRPC_DATA,
+D(2)    KM_SKB_DATA_SOFTIRQ,
+D(3)    KM_USER0,
+D(4)    KM_USER1,
+D(5)    KM_BIO_SRC_IRQ,
+D(6)    KM_BIO_DST_IRQ,
+D(7)    KM_PTE0,
+D(8)    KM_PTE1,
+D(9)    KM_IRQ0,
+D(10)   KM_IRQ1,
+D(11)   KM_SOFTIRQ0,
+D(12)   KM_SOFTIRQ1,
+D(13)   KM_TYPE_NR
+};
+
+#undef D
+
 #endif
diff --git a/include/asm-x86/kmap_types_32.h b/include/asm-x86/kmap_types_32.h
deleted file mode 100644
index 806aae3c5338..000000000000
--- a/include/asm-x86/kmap_types_32.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-# define D(n) __KM_FENCE_##n ,
-#else
-# define D(n)
-#endif
-
-enum km_type {
-D(0)    KM_BOUNCE_READ,
-D(1)    KM_SKB_SUNRPC_DATA,
-D(2)    KM_SKB_DATA_SOFTIRQ,
-D(3)    KM_USER0,
-D(4)    KM_USER1,
-D(5)    KM_BIO_SRC_IRQ,
-D(6)    KM_BIO_DST_IRQ,
-D(7)    KM_PTE0,
-D(8)    KM_PTE1,
-D(9)    KM_IRQ0,
-D(10)   KM_IRQ1,
-D(11)   KM_SOFTIRQ0,
-D(12)   KM_SOFTIRQ1,
-D(13)   KM_TYPE_NR
-};
-
-#undef D
-
-#endif
diff --git a/include/asm-x86/kmap_types_64.h b/include/asm-x86/kmap_types_64.h
deleted file mode 100644
index 7486338c6cea..000000000000
--- a/include/asm-x86/kmap_types_64.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-enum km_type {
-        KM_BOUNCE_READ,
-        KM_SKB_SUNRPC_DATA,
-        KM_SKB_DATA_SOFTIRQ,
-        KM_USER0,
-        KM_USER1,
-        KM_BIO_SRC_IRQ,
-        KM_BIO_DST_IRQ,
-        KM_IRQ0,
-        KM_IRQ1,
-        KM_SOFTIRQ0,
-        KM_SOFTIRQ1,
-        KM_TYPE_NR
-};
-
-#endif
diff --git a/include/asm-x86/ldt.h b/include/asm-x86/ldt.h
index 3d9cc20d2ba4..20c597242b53 100644
--- a/include/asm-x86/ldt.h
+++ b/include/asm-x86/ldt.h
@@ -1,13 +1,40 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "ldt_32.h"
-# else
-#  include "ldt_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "ldt_32.h"
-# else
-#  include "ldt_64.h"
-# endif
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef _ASM_X86_LDT_H
+#define _ASM_X86_LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES     8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE  8
+
+#ifndef __ASSEMBLY__
+/*
+ * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
+ * not to the default values if you still want to do syscalls. This
+ * call is more for 32bit mode therefore.
+ */
+struct user_desc {
+        unsigned int  entry_number;
+        unsigned int  base_addr;
+        unsigned int  limit;
+        unsigned int  seg_32bit:1;
+        unsigned int  contents:2;
+        unsigned int  read_exec_only:1;
+        unsigned int  limit_in_pages:1;
+        unsigned int  seg_not_present:1;
+        unsigned int  useable:1;
+#ifdef __x86_64__
+        unsigned int  lm:1;
+#endif
+};
+
+#define MODIFY_LDT_CONTENTS_DATA        0
+#define MODIFY_LDT_CONTENTS_STACK       1
+#define MODIFY_LDT_CONTENTS_CODE        2
+
+#endif /* !__ASSEMBLY__ */
 #endif
diff --git a/include/asm-x86/ldt_32.h b/include/asm-x86/ldt_32.h
deleted file mode 100644
index e9d3de1dee6c..000000000000
--- a/include/asm-x86/ldt_32.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * ldt.h
- *
- * Definitions of structures used with the modify_ldt system call.
- */
-#ifndef _LINUX_LDT_H
-#define _LINUX_LDT_H
-
-/* Maximum number of LDT entries supported. */
-#define LDT_ENTRIES     8192
-/* The size of each LDT entry. */
-#define LDT_ENTRY_SIZE  8
-
-#ifndef __ASSEMBLY__
-struct user_desc {
-        unsigned int  entry_number;
-        unsigned long base_addr;
-        unsigned int  limit;
-        unsigned int  seg_32bit:1;
-        unsigned int  contents:2;
-        unsigned int  read_exec_only:1;
-        unsigned int  limit_in_pages:1;
-        unsigned int  seg_not_present:1;
-        unsigned int  useable:1;
-};
-
-#define MODIFY_LDT_CONTENTS_DATA        0
-#define MODIFY_LDT_CONTENTS_STACK       1
-#define MODIFY_LDT_CONTENTS_CODE        2
-
-#endif /* !__ASSEMBLY__ */
-#endif
diff --git a/include/asm-x86/ldt_64.h b/include/asm-x86/ldt_64.h
deleted file mode 100644
index 9ef647b890d2..000000000000
--- a/include/asm-x86/ldt_64.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * ldt.h
- *
- * Definitions of structures used with the modify_ldt system call.
- */
-#ifndef _LINUX_LDT_H
-#define _LINUX_LDT_H
-
-/* Maximum number of LDT entries supported. */
-#define LDT_ENTRIES     8192
-/* The size of each LDT entry. */
-#define LDT_ENTRY_SIZE  8
-
-#ifndef __ASSEMBLY__
-/* Note on 64bit base and limit is ignored and you cannot set
-   DS/ES/CS not to the default values if you still want to do syscalls. This
-   call is more for 32bit mode therefore. */
-struct user_desc {
-        unsigned int  entry_number;
-        unsigned int  base_addr;
-        unsigned int  limit;
-        unsigned int  seg_32bit:1;
-        unsigned int  contents:2;
-        unsigned int  read_exec_only:1;
-        unsigned int  limit_in_pages:1;
-        unsigned int  seg_not_present:1;
-        unsigned int  useable:1;
-        unsigned int  lm:1;
-};
-
-#define MODIFY_LDT_CONTENTS_DATA        0
-#define MODIFY_LDT_CONTENTS_STACK       1
-#define MODIFY_LDT_CONTENTS_CODE        2
-
-#endif /* !__ASSEMBLY__ */
-#endif
diff --git a/include/asm-x86/mach-default/mach_apicdef.h b/include/asm-x86/mach-default/mach_apicdef.h
index 7bcb350c3ee8..ae9841319094 100644
--- a/include/asm-x86/mach-default/mach_apicdef.h
+++ b/include/asm-x86/mach-default/mach_apicdef.h
@@ -1,11 +1,17 @@
 #ifndef __ASM_MACH_APICDEF_H
 #define __ASM_MACH_APICDEF_H
 
+#include <asm/apic.h>
+
 #define         APIC_ID_MASK            (0xF<<24)
 
 static inline unsigned get_apic_id(unsigned long x) 
 { 
-        return (((x)>>24)&0xF);
+        unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+        if (APIC_XAPIC(ver))
+                return (((x)>>24)&0xFF);
+        else
+                return (((x)>>24)&0xF);
 } 
 
 #define         GET_APIC_ID(x)  get_apic_id(x)
diff --git a/include/asm-x86/mach-visws/cobalt.h b/include/asm-x86/mach-visws/cobalt.h
index 33c36225a042..995258831b7f 100644
--- a/include/asm-x86/mach-visws/cobalt.h
+++ b/include/asm-x86/mach-visws/cobalt.h
@@ -94,22 +94,22 @@
 #define CO_IRQ_8259     CO_IRQ(CO_APIC_8259)
 
 #ifdef CONFIG_X86_VISWS_APIC
-extern __inline void co_cpu_write(unsigned long reg, unsigned long v)
+static inline void co_cpu_write(unsigned long reg, unsigned long v)
 {
         *((volatile unsigned long *)(CO_CPU_VADDR+reg))=v;
 }
 
-extern __inline unsigned long co_cpu_read(unsigned long reg)
+static inline unsigned long co_cpu_read(unsigned long reg)
 {
         return *((volatile unsigned long *)(CO_CPU_VADDR+reg));
 }            
              
-extern __inline void co_apic_write(unsigned long reg, unsigned long v)
+static inline void co_apic_write(unsigned long reg, unsigned long v)
 {
         *((volatile unsigned long *)(CO_APIC_VADDR+reg))=v;
 }            
              
-extern __inline unsigned long co_apic_read(unsigned long reg)
+static inline unsigned long co_apic_read(unsigned long reg)
 {
         return *((volatile unsigned long *)(CO_APIC_VADDR+reg));
 }
diff --git a/include/asm-x86/mach-visws/lithium.h b/include/asm-x86/mach-visws/lithium.h
index d443e68d0066..dfcd4f07ab85 100644
--- a/include/asm-x86/mach-visws/lithium.h
+++ b/include/asm-x86/mach-visws/lithium.h
@@ -29,22 +29,22 @@
 #define LI_INTD         0x0080
 
 /* More special purpose macros... */
-extern __inline void li_pcia_write16(unsigned long reg, unsigned short v)
+static inline void li_pcia_write16(unsigned long reg, unsigned short v)
 {
         *((volatile unsigned short *)(LI_PCIA_VADDR+reg))=v;
 }
 
-extern __inline unsigned short li_pcia_read16(unsigned long reg)
+static inline unsigned short li_pcia_read16(unsigned long reg)
 {
          return *((volatile unsigned short *)(LI_PCIA_VADDR+reg));
 }
 
-extern __inline void li_pcib_write16(unsigned long reg, unsigned short v)
+static inline void li_pcib_write16(unsigned long reg, unsigned short v)
 {
         *((volatile unsigned short *)(LI_PCIB_VADDR+reg))=v;
 }
 
-extern __inline unsigned short li_pcib_read16(unsigned long reg)
+static inline unsigned short li_pcib_read16(unsigned long reg)
 {
         return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
 }
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
index cc8ca389912e..df304fd89c27 100644
--- a/include/asm-x86/mce.h
+++ b/include/asm-x86/mce.h
@@ -1,5 +1,129 @@
+#ifndef _ASM_X86_MCE_H
+#define _ASM_X86_MCE_H
+
+#ifdef __x86_64__
+
+#include <asm/ioctls.h>
+#include <asm/types.h>
+
+/*
+ * Machine Check support for x86
+ */
+
+#define MCG_CTL_P        (1UL<<8)   /* MCG_CAP register available */
+
+#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1UL<<1)   /* eip points to correct instruction */
+#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
+
+#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
+
+/* Fields are zero when not available */
+struct mce {
+        __u64 status;
+        __u64 misc;
+        __u64 addr;
+        __u64 mcgstatus;
+        __u64 rip;
+        __u64 tsc;      /* cpu time stamp counter */
+        __u64 res1;     /* for future extension */
+        __u64 res2;     /* dito. */
+        __u8  cs;               /* code segment */
+        __u8  bank;     /* machine check bank */
+        __u8  cpu;      /* cpu that raised the error */
+        __u8  finished;   /* entry is valid */
+        __u32 pad;
+};
+
+/*
+ * This structure contains all data related to the MCE log.  Also
+ * carries a signature to make it easier to find from external
+ * debugging tools.  Each entry is only valid when its finished flag
+ * is set.
+ */
+
+#define MCE_LOG_LEN 32
+
+struct mce_log {
+        char signature[12]; /* "MACHINECHECK" */
+        unsigned len;       /* = MCE_LOG_LEN */
+        unsigned next;
+        unsigned flags;
+        unsigned pad0;
+        struct mce entry[MCE_LOG_LEN];
+};
+
+#define MCE_OVERFLOW 0          /* bit 0 in flags means overflow */
+
+#define MCE_LOG_SIGNATURE       "MACHINECHECK"
+
+#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
+#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
+#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
+
+/* Software defined banks */
+#define MCE_EXTENDED_BANK       128
+#define MCE_THERMAL_BANK        MCE_EXTENDED_BANK + 0
+
+#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)      /* MCE_AMD */
+#define K8_MCE_THRESHOLD_BANK_0    (MCE_THRESHOLD_BASE + 0 * 9)
+#define K8_MCE_THRESHOLD_BANK_1    (MCE_THRESHOLD_BASE + 1 * 9)
+#define K8_MCE_THRESHOLD_BANK_2    (MCE_THRESHOLD_BASE + 2 * 9)
+#define K8_MCE_THRESHOLD_BANK_3    (MCE_THRESHOLD_BASE + 3 * 9)
+#define K8_MCE_THRESHOLD_BANK_4    (MCE_THRESHOLD_BASE + 4 * 9)
+#define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
+#define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
+
+#endif /* __x86_64__ */
+
+#ifdef __KERNEL__
+
 #ifdef CONFIG_X86_32
-# include "mce_32.h"
+#ifdef CONFIG_X86_MCE
+extern void mcheck_init(struct cpuinfo_x86 *c);
 #else
-# include "mce_64.h"
+#define mcheck_init(c) do {} while(0)
+#endif
+
+extern int mce_disabled;
+
+#else /* CONFIG_X86_32 */
+
+#include <asm/atomic.h>
+
+void mce_log(struct mce *m);
+DECLARE_PER_CPU(struct sys_device, device_mce);
+
+#ifdef CONFIG_X86_MCE_INTEL
+void mce_intel_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
+#endif
+
+void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
+
+extern atomic_t mce_entry;
+
+extern void do_machine_check(struct pt_regs *, long);
+extern int mce_notify_user(void);
+
+#endif /* !CONFIG_X86_32 */
+
+extern void stop_mce(void);
+extern void restart_mce(void);
+
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/include/asm-x86/mce_32.h b/include/asm-x86/mce_32.h
deleted file mode 100644
index d56d89742e8f..000000000000
--- a/include/asm-x86/mce_32.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifdef CONFIG_X86_MCE
-extern void mcheck_init(struct cpuinfo_x86 *c);
-#else
-#define mcheck_init(c) do {} while(0)
-#endif
-
-extern int mce_disabled;
-
-extern void stop_mce(void);
-extern void restart_mce(void);
-
diff --git a/include/asm-x86/mce_64.h b/include/asm-x86/mce_64.h
deleted file mode 100644
index 7bc030a1996d..000000000000
--- a/include/asm-x86/mce_64.h
+++ /dev/null
@@ -1,115 +0,0 @@
-#ifndef _ASM_MCE_H
-#define _ASM_MCE_H 1
-
-#include <asm/ioctls.h>
-#include <asm/types.h>
-
-/* 
- * Machine Check support for x86
- */
-
-#define MCG_CTL_P        (1UL<<8)   /* MCG_CAP register available */
-
-#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV  (1UL<<1)   /* eip points to correct instruction */
-#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
-
-#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
-#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
-#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
-
-/* Fields are zero when not available */
-struct mce {
-        __u64 status;
-        __u64 misc;
-        __u64 addr;
-        __u64 mcgstatus;
-        __u64 rip;      
-        __u64 tsc;      /* cpu time stamp counter */
-        __u64 res1;     /* for future extension */      
-        __u64 res2;     /* dito. */
-        __u8  cs;               /* code segment */
-        __u8  bank;     /* machine check bank */
-        __u8  cpu;      /* cpu that raised the error */
-        __u8  finished;   /* entry is valid */
-        __u32 pad;   
-};
-
-/* 
- * This structure contains all data related to the MCE log.
- * Also carries a signature to make it easier to find from external debugging tools.
- * Each entry is only valid when its finished flag is set.
- */
-
-#define MCE_LOG_LEN 32
-
-struct mce_log { 
-        char signature[12]; /* "MACHINECHECK" */ 
-        unsigned len;       /* = MCE_LOG_LEN */ 
-        unsigned next;
-        unsigned flags;
-        unsigned pad0; 
-        struct mce entry[MCE_LOG_LEN];
-};
-
-#define MCE_OVERFLOW 0          /* bit 0 in flags means overflow */
-
-#define MCE_LOG_SIGNATURE       "MACHINECHECK"
-
-#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
-#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
-#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
-
-/* Software defined banks */
-#define MCE_EXTENDED_BANK       128
-#define MCE_THERMAL_BANK        MCE_EXTENDED_BANK + 0
-
-#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)      /* MCE_AMD */
-#define K8_MCE_THRESHOLD_BANK_0    (MCE_THRESHOLD_BASE + 0 * 9)
-#define K8_MCE_THRESHOLD_BANK_1    (MCE_THRESHOLD_BASE + 1 * 9)
-#define K8_MCE_THRESHOLD_BANK_2    (MCE_THRESHOLD_BASE + 2 * 9)
-#define K8_MCE_THRESHOLD_BANK_3    (MCE_THRESHOLD_BASE + 3 * 9)
-#define K8_MCE_THRESHOLD_BANK_4    (MCE_THRESHOLD_BASE + 4 * 9)
-#define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
-#define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
-
-#ifdef __KERNEL__
-#include <asm/atomic.h>
-
-void mce_log(struct mce *m);
-DECLARE_PER_CPU(struct sys_device, device_mce);
-
-#ifdef CONFIG_X86_MCE_INTEL
-void mce_intel_feature_init(struct cpuinfo_x86 *c);
-#else
-static inline void mce_intel_feature_init(struct cpuinfo_x86 *c)
-{
-}
-#endif
-
-#ifdef CONFIG_X86_MCE_AMD
-void mce_amd_feature_init(struct cpuinfo_x86 *c);
-#else
-static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)
-{
-}
-#endif
-
-void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
-
-extern atomic_t mce_entry;
-
-extern void do_machine_check(struct pt_regs *, long);
-
-extern int mce_notify_user(void);
-
-extern void stop_mce(void);
-extern void restart_mce(void);
-
-#endif
-
-#endif
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
index 322db07e82c3..c1682b542daf 100644
--- a/include/asm-x86/mman.h
+++ b/include/asm-x86/mman.h
@@ -1,13 +1,19 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "mman_32.h"
-# else
-#  include "mman_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "mman_32.h"
-# else
-#  include "mman_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_MMAN_H
+#define _ASM_X86_MMAN_H
+
+#include <asm-generic/mman.h>
+
+#define MAP_32BIT       0x40            /* only give out 32bit addresses */
+
+#define MAP_GROWSDOWN   0x0100          /* stack-like segment */
+#define MAP_DENYWRITE   0x0800          /* ETXTBSY */
+#define MAP_EXECUTABLE  0x1000          /* mark it as an executable */
+#define MAP_LOCKED      0x2000          /* pages are locked */
+#define MAP_NORESERVE   0x4000          /* don't check for reservations */
+#define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
+#define MAP_NONBLOCK    0x10000         /* do not block on IO */
+
+#define MCL_CURRENT     1               /* lock all current mappings */
+#define MCL_FUTURE      2               /* lock all future mappings */
+
+#endif /* _ASM_X86_MMAN_H */
diff --git a/include/asm-x86/mman_32.h b/include/asm-x86/mman_32.h
deleted file mode 100644
index 8fd9d7ab7faf..000000000000
--- a/include/asm-x86/mman_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef __I386_MMAN_H__
-#define __I386_MMAN_H__
-
-#include <asm-generic/mman.h>
-
-#define MAP_GROWSDOWN   0x0100          /* stack-like segment */
-#define MAP_DENYWRITE   0x0800          /* ETXTBSY */
-#define MAP_EXECUTABLE  0x1000          /* mark it as an executable */
-#define MAP_LOCKED      0x2000          /* pages are locked */
-#define MAP_NORESERVE   0x4000          /* don't check for reservations */
-#define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
-#define MAP_NONBLOCK    0x10000         /* do not block on IO */
-
-#define MCL_CURRENT     1               /* lock all current mappings */
-#define MCL_FUTURE      2               /* lock all future mappings */
-
-#endif /* __I386_MMAN_H__ */
diff --git a/include/asm-x86/mman_64.h b/include/asm-x86/mman_64.h
deleted file mode 100644
index dd5cb0534d37..000000000000
--- a/include/asm-x86/mman_64.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef __X8664_MMAN_H__
-#define __X8664_MMAN_H__
-
-#include <asm-generic/mman.h>
-
-#define MAP_32BIT       0x40            /* only give out 32bit addresses */
-
-#define MAP_GROWSDOWN   0x0100          /* stack-like segment */
-#define MAP_DENYWRITE   0x0800          /* ETXTBSY */
-#define MAP_EXECUTABLE  0x1000          /* mark it as an executable */
-#define MAP_LOCKED      0x2000          /* pages are locked */
-#define MAP_NORESERVE   0x4000          /* don't check for reservations */
-#define MAP_POPULATE    0x8000          /* populate (prefault) pagetables */
-#define MAP_NONBLOCK    0x10000         /* do not block on IO */
-
-#define MCL_CURRENT     1               /* lock all current mappings */
-#define MCL_FUTURE      2               /* lock all future mappings */
-
-#endif
diff --git a/include/asm-x86/mmu_32.h b/include/asm-x86/mmu_32.h
index 8358dd3df7aa..5e249c51ef56 100644
--- a/include/asm-x86/mmu_32.h
+++ b/include/asm-x86/mmu_32.h
@@ -1,7 +1,7 @@
 #ifndef __i386_MMU_H
 #define __i386_MMU_H
 
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 /*
  * The i386 doesn't have a mmu context, but
  * we put the segment information here.
@@ -10,7 +10,7 @@
  */
 typedef struct { 
         int size;
-        struct semaphore sem;
+        struct mutex lock;
         void *ldt;
         void *vdso;
 } mm_context_t;
diff --git a/include/asm-x86/mmu_64.h b/include/asm-x86/mmu_64.h
index d2cd4a9d984d..024357c27222 100644
--- a/include/asm-x86/mmu_64.h
+++ b/include/asm-x86/mmu_64.h
@@ -2,7 +2,7 @@
 #define __x86_64_MMU_H
 
 #include <linux/spinlock.h>
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 
 /*
  * The x86_64 doesn't have a mmu context, but
@@ -14,7 +14,7 @@ typedef struct {
         void *ldt;
         rwlock_t ldtlock; 
         int size;
-        struct semaphore sem; 
+        struct mutex lock;
         void *vdso;
 } mm_context_t;
 
diff --git a/include/asm-x86/namei.h b/include/asm-x86/namei.h
index 732f8f0b3dcd..415ef5d9550e 100644
--- a/include/asm-x86/namei.h
+++ b/include/asm-x86/namei.h
@@ -1,5 +1,11 @@
-#ifdef CONFIG_X86_32
-# include "namei_32.h"
-#else
-# include "namei_64.h"
-#endif
+#ifndef _ASM_X86_NAMEI_H
+#define _ASM_X86_NAMEI_H
+
+/* This dummy routine maybe changed to something useful
+ * for /usr/gnemul/ emulation stuff.
+ * Look at asm-sparc/namei.h for details.
+ */
+
+#define __emul_prefix() NULL
+
+#endif /* _ASM_X86_NAMEI_H */
diff --git a/include/asm-x86/namei_32.h b/include/asm-x86/namei_32.h
deleted file mode 100644
index 814865088617..000000000000
--- a/include/asm-x86/namei_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* $Id: namei.h,v 1.1 1996/12/13 14:48:21 jj Exp $
- * linux/include/asm-i386/namei.h
- *
- * Included from linux/fs/namei.c
- */
-
-#ifndef __I386_NAMEI_H
-#define __I386_NAMEI_H
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-
-#define __emul_prefix() NULL
-
-#endif /* __I386_NAMEI_H */
diff --git a/include/asm-x86/namei_64.h b/include/asm-x86/namei_64.h
deleted file mode 100644
index bef239f5318f..000000000000
--- a/include/asm-x86/namei_64.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __X8664_NAMEI_H
-#define __X8664_NAMEI_H
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-
-#define __emul_prefix() NULL
-
-#endif
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 933ff11ece15..0cc5c97a7fc9 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -2,6 +2,7 @@
 #define _ASM_X8664_NUMA_H 1
 
 #include <linux/nodemask.h>
+#include <asm/apicdef.h>
 
 struct bootnode {
         u64 start,end; 
@@ -19,7 +20,7 @@ extern void numa_set_node(int cpu, int node);
 extern void srat_reserve_add_area(int nodeid);
 extern int hotadd_percent;
 
-extern unsigned char apicid_to_node[256];
+extern unsigned char apicid_to_node[MAX_LOCAL_APIC];
 #ifdef CONFIG_NUMA
 extern void __init init_cpu_to_node(void);
 
diff --git a/include/asm-x86/param.h b/include/asm-x86/param.h
index 640851bab124..c996ec4da0c8 100644
--- a/include/asm-x86/param.h
+++ b/include/asm-x86/param.h
@@ -1,13 +1,22 @@
+#ifndef _ASM_X86_PARAM_H
+#define _ASM_X86_PARAM_H
+
 #ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "param_32.h"
-# else
-#  include "param_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "param_32.h"
-# else
-#  include "param_64.h"
-# endif
+# define HZ             CONFIG_HZ       /* Internal kernel timer frequency */
+# define USER_HZ        100             /* .. some user interfaces are in "ticks" */
+# define CLOCKS_PER_SEC (USER_HZ)       /* like times() */
 #endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE   4096
+
+#ifndef NOGROUP
+#define NOGROUP         (-1)
+#endif
+
+#define MAXHOSTNAMELEN  64      /* max length of hostname */
+
+#endif /* _ASM_X86_PARAM_H */
diff --git a/include/asm-x86/param_32.h b/include/asm-x86/param_32.h
deleted file mode 100644
index 21b32466fcdc..000000000000
--- a/include/asm-x86/param_32.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASMi386_PARAM_H
-#define _ASMi386_PARAM_H
-
-#ifdef __KERNEL__
-# define HZ             CONFIG_HZ       /* Internal kernel timer frequency */
-# define USER_HZ        100             /* .. some user interfaces are in "ticks" */
-# define CLOCKS_PER_SEC         (USER_HZ)       /* like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE   4096
-
-#ifndef NOGROUP
-#define NOGROUP         (-1)
-#endif
-
-#define MAXHOSTNAMELEN  64      /* max length of hostname */
-
-#endif
diff --git a/include/asm-x86/param_64.h b/include/asm-x86/param_64.h
deleted file mode 100644
index a728786c3c7c..000000000000
--- a/include/asm-x86/param_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASMx86_64_PARAM_H
-#define _ASMx86_64_PARAM_H
-
-#ifdef __KERNEL__
-# define HZ            CONFIG_HZ        /* Internal kernel timer frequency */
-# define USER_HZ       100              /* .. some user interfaces are in "ticks */
-#define CLOCKS_PER_SEC        (USER_HZ)       /* like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE   4096
-
-#ifndef NOGROUP
-#define NOGROUP         (-1)
-#endif
-
-#define MAXHOSTNAMELEN  64      /* max length of hostname */
-
-#endif
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 9fa3fa9e62d1..f59d370c5df4 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -25,27 +25,22 @@ struct tss_struct;
 struct mm_struct;
 struct desc_struct;
 
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
-        PARAVIRT_LAZY_NONE = 0,
-        PARAVIRT_LAZY_MMU = 1,
-        PARAVIRT_LAZY_CPU = 2,
-        PARAVIRT_LAZY_FLUSH = 3,
-};
-
-struct paravirt_ops
-{
+/* general info */
+struct pv_info {
         unsigned int kernel_rpl;
         int shared_kernel_pmd;
-        int paravirt_enabled;
+        int paravirt_enabled;
         const char *name;
+};
 
+struct pv_init_ops {
         /*
-         * Patch may replace one of the defined code sequences with arbitrary
-         * code, subject to the same register constraints.  This generally
-         * means the code is not free to clobber any registers other than EAX.
-         * The patch function should return the number of bytes of code
-         * generated, as we nop pad the rest in generic code.
+         * Patch may replace one of the defined code sequences with
+         * arbitrary code, subject to the same register constraints.
+         * This generally means the code is not free to clobber any
+         * registers other than EAX.  The patch function should return
+         * the number of bytes of code generated, as we nop pad the
+         * rest in generic code.
          */
         unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
                           unsigned long addr, unsigned len);
@@ -55,29 +50,29 @@ struct paravirt_ops
         char *(*memory_setup)(void);
         void (*post_allocator_init)(void);
 
-        void (*init_IRQ)(void);
-        void (*time_init)(void);
-
-        /*
-         * Called before/after init_mm pagetable setup. setup_start
-         * may reset %cr3, and may pre-install parts of the pagetable;
-         * pagetable setup is expected to preserve any existing
-         * mapping.
-         */
-        void (*pagetable_setup_start)(pgd_t *pgd_base);
-        void (*pagetable_setup_done)(pgd_t *pgd_base);
-
         /* Print a banner to identify the environment */
         void (*banner)(void);
+};
+
+
+struct pv_lazy_ops {
+        /* Set deferred update mode, used for batching operations. */
+        void (*enter)(void);
+        void (*leave)(void);
+};
+
+struct pv_time_ops {
+        void (*time_init)(void);
 
         /* Set and set time of day */
         unsigned long (*get_wallclock)(void);
         int (*set_wallclock)(unsigned long);
 
-        /* cpuid emulation, mostly so that caps bits can be disabled */
-        void (*cpuid)(unsigned int *eax, unsigned int *ebx,
-                      unsigned int *ecx, unsigned int *edx);
+        unsigned long long (*sched_clock)(void);
+        unsigned long (*get_cpu_khz)(void);
+};
 
+struct pv_cpu_ops {
         /* hooks for various privileged instructions */
         unsigned long (*get_debugreg)(int regno);
         void (*set_debugreg)(int regno, unsigned long value);
@@ -87,41 +82,10 @@ struct paravirt_ops
         unsigned long (*read_cr0)(void);
         void (*write_cr0)(unsigned long);
 
-        unsigned long (*read_cr2)(void);
-        void (*write_cr2)(unsigned long);
-
-        unsigned long (*read_cr3)(void);
-        void (*write_cr3)(unsigned long);
-
         unsigned long (*read_cr4_safe)(void);
         unsigned long (*read_cr4)(void);
         void (*write_cr4)(unsigned long);
 
-        /*
-         * Get/set interrupt state.  save_fl and restore_fl are only
-         * expected to use X86_EFLAGS_IF; all other bits
-         * returned from save_fl are undefined, and may be ignored by
-         * restore_fl.
-         */
-        unsigned long (*save_fl)(void);
-        void (*restore_fl)(unsigned long);
-        void (*irq_disable)(void);
-        void (*irq_enable)(void);
-        void (*safe_halt)(void);
-        void (*halt)(void);
-
-        void (*wbinvd)(void);
-
-        /* MSR, PMC and TSR operations.
-           err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
-        u64 (*read_msr)(unsigned int msr, int *err);
-        int (*write_msr)(unsigned int msr, u64 val);
-
-        u64 (*read_tsc)(void);
-        u64 (*read_pmc)(void);
-        unsigned long long (*sched_clock)(void);
-        unsigned long (*get_cpu_khz)(void);
-
         /* Segment descriptor handling */
         void (*load_tr_desc)(void);
         void (*load_gdt)(const struct Xgt_desc_struct *);
@@ -140,18 +104,47 @@ struct paravirt_ops
         void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t);
 
         void (*set_iopl_mask)(unsigned mask);
+
+        void (*wbinvd)(void);
         void (*io_delay)(void);
 
+        /* cpuid emulation, mostly so that caps bits can be disabled */
+        void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+                      unsigned int *ecx, unsigned int *edx);
+
+        /* MSR, PMC and TSR operations.
+           err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+        u64 (*read_msr)(unsigned int msr, int *err);
+        int (*write_msr)(unsigned int msr, u64 val);
+
+        u64 (*read_tsc)(void);
+        u64 (*read_pmc)(void);
+
+        /* These two are jmp to, not actually called. */
+        void (*irq_enable_sysexit)(void);
+        void (*iret)(void);
+
+        struct pv_lazy_ops lazy_mode;
+};
+
+struct pv_irq_ops {
+        void (*init_IRQ)(void);
+
         /*
-         * Hooks for intercepting the creation/use/destruction of an
-         * mm_struct.
+         * Get/set interrupt state.  save_fl and restore_fl are only
+         * expected to use X86_EFLAGS_IF; all other bits
+         * returned from save_fl are undefined, and may be ignored by
+         * restore_fl.
          */
-        void (*activate_mm)(struct mm_struct *prev,
-                            struct mm_struct *next);
-        void (*dup_mmap)(struct mm_struct *oldmm,
-                         struct mm_struct *mm);
-        void (*exit_mmap)(struct mm_struct *mm);
+        unsigned long (*save_fl)(void);
+        void (*restore_fl)(unsigned long);
+        void (*irq_disable)(void);
+        void (*irq_enable)(void);
+        void (*safe_halt)(void);
+        void (*halt)(void);
+};
 
+struct pv_apic_ops {
 #ifdef CONFIG_X86_LOCAL_APIC
         /*
          * Direct APIC operations, principally for VMI.  Ideally
@@ -167,6 +160,34 @@ struct paravirt_ops
                                  unsigned long start_eip,
                                  unsigned long start_esp);
 #endif
+};
+
+struct pv_mmu_ops {
+        /*
+         * Called before/after init_mm pagetable setup. setup_start
+         * may reset %cr3, and may pre-install parts of the pagetable;
+         * pagetable setup is expected to preserve any existing
+         * mapping.
+         */
+        void (*pagetable_setup_start)(pgd_t *pgd_base);
+        void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+        unsigned long (*read_cr2)(void);
+        void (*write_cr2)(unsigned long);
+
+        unsigned long (*read_cr3)(void);
+        void (*write_cr3)(unsigned long);
+
+        /*
+         * Hooks for intercepting the creation/use/destruction of an
+         * mm_struct.
+         */
+        void (*activate_mm)(struct mm_struct *prev,
+                            struct mm_struct *next);
+        void (*dup_mmap)(struct mm_struct *oldmm,
+                         struct mm_struct *mm);
+        void (*exit_mmap)(struct mm_struct *mm);
+
 
         /* TLB operations */
         void (*flush_tlb_user)(void);
@@ -191,15 +212,12 @@ struct paravirt_ops
         void (*pte_update_defer)(struct mm_struct *mm,
                                  unsigned long addr, pte_t *ptep);
 
-#ifdef CONFIG_HIGHPTE
-        void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
-#endif
-
 #ifdef CONFIG_X86_PAE
         void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
-        void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+        void (*set_pte_present)(struct mm_struct *mm, unsigned long addr,
+                                pte_t *ptep, pte_t pte);
         void (*set_pud)(pud_t *pudp, pud_t pudval);
-        void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+        void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
         void (*pmd_clear)(pmd_t *pmdp);
 
         unsigned long long (*pte_val)(pte_t);
@@ -217,21 +235,40 @@ struct paravirt_ops
         pgd_t (*make_pgd)(unsigned long pgd);
 #endif
 
-        /* Set deferred update mode, used for batching operations. */
-        void (*set_lazy_mode)(enum paravirt_lazy_mode mode);
+#ifdef CONFIG_HIGHPTE
+        void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
 
-        /* These two are jmp to, not actually called. */
-        void (*irq_enable_sysexit)(void);
-        void (*iret)(void);
+        struct pv_lazy_ops lazy_mode;
 };
 
-extern struct paravirt_ops paravirt_ops;
+/* This contains all the paravirt structures: we get a convenient
+ * number for each function using the offset which we use to indicate
+ * what to patch. */
+struct paravirt_patch_template
+{
+        struct pv_init_ops pv_init_ops;
+        struct pv_time_ops pv_time_ops;
+        struct pv_cpu_ops pv_cpu_ops;
+        struct pv_irq_ops pv_irq_ops;
+        struct pv_apic_ops pv_apic_ops;
+        struct pv_mmu_ops pv_mmu_ops;
+};
+
+extern struct pv_info pv_info;
+extern struct pv_init_ops pv_init_ops;
+extern struct pv_time_ops pv_time_ops;
+extern struct pv_cpu_ops pv_cpu_ops;
+extern struct pv_irq_ops pv_irq_ops;
+extern struct pv_apic_ops pv_apic_ops;
+extern struct pv_mmu_ops pv_mmu_ops;
 
 #define PARAVIRT_PATCH(x)                                       \
-        (offsetof(struct paravirt_ops, x) / sizeof(void *))
+        (offsetof(struct paravirt_patch_template, x) / sizeof(void *))
 
-#define paravirt_type(type)                                     \
-        [paravirt_typenum] "i" (PARAVIRT_PATCH(type))
+#define paravirt_type(op)                               \
+        [paravirt_typenum] "i" (PARAVIRT_PATCH(op)),    \
+        [paravirt_opptr] "m" (op)
 #define paravirt_clobber(clobber)               \
         [paravirt_clobber] "i" (clobber)
 
@@ -258,7 +295,7 @@ unsigned paravirt_patch_call(void *insnbuf,
                              const void *target, u16 tgt_clobbers,
                              unsigned long addr, u16 site_clobbers,
                              unsigned len);
-unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
                             unsigned long addr, unsigned len);
 unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
                                 unsigned long addr, unsigned len);
@@ -271,14 +308,14 @@ int paravirt_disable_iospace(void);
 /*
  * This generates an indirect call based on the operation type number.
  * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_ops structure, and can therefore be freely
- * converted back into a structure offset.
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL   "call *(paravirt_ops+%c[paravirt_typenum]*4);"
+#define PARAVIRT_CALL   "call *%[paravirt_opptr];"
 
 /*
- * These macros are intended to wrap calls into a paravirt_ops
- * operation, so that they can be later identified and patched at
+ * These macros are intended to wrap calls through one of the paravirt
+ * ops structs, so that they can be later identified and patched at
  * runtime.
  *
  * Normally, a call to a pv_op function is a simple indirect call:
@@ -301,7 +338,7 @@ int paravirt_disable_iospace(void);
  * The call instruction itself is marked by placing its start address
  * and size into the .parainstructions section, so that
  * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend paravirt_ops
+ * appropriate patching under the control of the backend pv_init_ops
  * implementation.
  *
  * Unfortunately there's no way to get gcc to generate the args setup
@@ -409,36 +446,36 @@ int paravirt_disable_iospace(void);
 
 static inline int paravirt_enabled(void)
 {
-        return paravirt_ops.paravirt_enabled;
+        return pv_info.paravirt_enabled;
 }
 
 static inline void load_esp0(struct tss_struct *tss,
                              struct thread_struct *thread)
 {
-        PVOP_VCALL2(load_esp0, tss, thread);
+        PVOP_VCALL2(pv_cpu_ops.load_esp0, tss, thread);
 }
 
-#define ARCH_SETUP                      paravirt_ops.arch_setup();
+#define ARCH_SETUP                      pv_init_ops.arch_setup();
 static inline unsigned long get_wallclock(void)
 {
-        return PVOP_CALL0(unsigned long, get_wallclock);
+        return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock);
 }
 
 static inline int set_wallclock(unsigned long nowtime)
 {
-        return PVOP_CALL1(int, set_wallclock, nowtime);
+        return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime);
 }
 
 static inline void (*choose_time_init(void))(void)
 {
-        return paravirt_ops.time_init;
+        return pv_time_ops.time_init;
 }
 
 /* The paravirtualized CPUID instruction. */
 static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
                            unsigned int *ecx, unsigned int *edx)
 {
-        PVOP_VCALL4(cpuid, eax, ebx, ecx, edx);
+        PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
 }
 
 /*
@@ -446,87 +483,87 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
  */
 static inline unsigned long paravirt_get_debugreg(int reg)
 {
-        return PVOP_CALL1(unsigned long, get_debugreg, reg);
+        return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
 }
 #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
 static inline void set_debugreg(unsigned long val, int reg)
 {
-        PVOP_VCALL2(set_debugreg, reg, val);
+        PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
 }
 
 static inline void clts(void)
 {
-        PVOP_VCALL0(clts);
+        PVOP_VCALL0(pv_cpu_ops.clts);
 }
 
 static inline unsigned long read_cr0(void)
 {
-        return PVOP_CALL0(unsigned long, read_cr0);
+        return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
 }
 
 static inline void write_cr0(unsigned long x)
 {
-        PVOP_VCALL1(write_cr0, x);
+        PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
 }
 
 static inline unsigned long read_cr2(void)
 {
-        return PVOP_CALL0(unsigned long, read_cr2);
+        return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
 }
 
 static inline void write_cr2(unsigned long x)
 {
-        PVOP_VCALL1(write_cr2, x);
+        PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
 }
 
 static inline unsigned long read_cr3(void)
 {
-        return PVOP_CALL0(unsigned long, read_cr3);
+        return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
 }
 
 static inline void write_cr3(unsigned long x)
 {
-        PVOP_VCALL1(write_cr3, x);
+        PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
 }
 
 static inline unsigned long read_cr4(void)
 {
-        return PVOP_CALL0(unsigned long, read_cr4);
+        return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
 }
 static inline unsigned long read_cr4_safe(void)
 {
-        return PVOP_CALL0(unsigned long, read_cr4_safe);
+        return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
 }
 
 static inline void write_cr4(unsigned long x)
 {
-        PVOP_VCALL1(write_cr4, x);
+        PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
 }
 
 static inline void raw_safe_halt(void)
 {
-        PVOP_VCALL0(safe_halt);
+        PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
 
 static inline void halt(void)
 {
-        PVOP_VCALL0(safe_halt);
+        PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
 
 static inline void wbinvd(void)
 {
-        PVOP_VCALL0(wbinvd);
+        PVOP_VCALL0(pv_cpu_ops.wbinvd);
 }
 
-#define get_kernel_rpl()  (paravirt_ops.kernel_rpl)
+#define get_kernel_rpl()  (pv_info.kernel_rpl)
 
 static inline u64 paravirt_read_msr(unsigned msr, int *err)
 {
-        return PVOP_CALL2(u64, read_msr, msr, err);
+        return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
-        return PVOP_CALL3(int, write_msr, msr, low, high);
+        return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
 }
 
 /* These should all do BUG_ON(_err), but our headers are too tangled. */
@@ -560,7 +597,7 @@ static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 
 static inline u64 paravirt_read_tsc(void)
 {
-        return PVOP_CALL0(u64, read_tsc);
+        return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
 }
 
 #define rdtscl(low) do {                        \
@@ -572,15 +609,15 @@ static inline u64 paravirt_read_tsc(void)
 
 static inline unsigned long long paravirt_sched_clock(void)
 {
-        return PVOP_CALL0(unsigned long long, sched_clock);
+        return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
-#define calculate_cpu_khz() (paravirt_ops.get_cpu_khz())
+#define calculate_cpu_khz() (pv_time_ops.get_cpu_khz())
 
 #define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
 
 static inline unsigned long long paravirt_read_pmc(int counter)
 {
-        return PVOP_CALL1(u64, read_pmc, counter);
+        return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
 }
 
 #define rdpmc(counter,low,high) do {            \
@@ -591,61 +628,61 @@ static inline unsigned long long paravirt_read_pmc(int counter)
 
 static inline void load_TR_desc(void)
 {
-        PVOP_VCALL0(load_tr_desc);
+        PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
 }
 static inline void load_gdt(const struct Xgt_desc_struct *dtr)
 {
-        PVOP_VCALL1(load_gdt, dtr);
+        PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
 }
 static inline void load_idt(const struct Xgt_desc_struct *dtr)
 {
-        PVOP_VCALL1(load_idt, dtr);
+        PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
 }
 static inline void set_ldt(const void *addr, unsigned entries)
 {
-        PVOP_VCALL2(set_ldt, addr, entries);
+        PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
 }
 static inline void store_gdt(struct Xgt_desc_struct *dtr)
 {
-        PVOP_VCALL1(store_gdt, dtr);
+        PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
 }
 static inline void store_idt(struct Xgt_desc_struct *dtr)
 {
-        PVOP_VCALL1(store_idt, dtr);
+        PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
 }
 static inline unsigned long paravirt_store_tr(void)
 {
-        return PVOP_CALL0(unsigned long, store_tr);
+        return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
 }
 #define store_tr(tr)    ((tr) = paravirt_store_tr())
 static inline void load_TLS(struct thread_struct *t, unsigned cpu)
 {
-        PVOP_VCALL2(load_tls, t, cpu);
+        PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
 }
 static inline void write_ldt_entry(void *dt, int entry, u32 low, u32 high)
 {
-        PVOP_VCALL4(write_ldt_entry, dt, entry, low, high);
+        PVOP_VCALL4(pv_cpu_ops.write_ldt_entry, dt, entry, low, high);
 }
 static inline void write_gdt_entry(void *dt, int entry, u32 low, u32 high)
 {
-        PVOP_VCALL4(write_gdt_entry, dt, entry, low, high);
+        PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, low, high);
 }
 static inline void write_idt_entry(void *dt, int entry, u32 low, u32 high)
 {
-        PVOP_VCALL4(write_idt_entry, dt, entry, low, high);
+        PVOP_VCALL4(pv_cpu_ops.write_idt_entry, dt, entry, low, high);
 }
 static inline void set_iopl_mask(unsigned mask)
 {
-        PVOP_VCALL1(set_iopl_mask, mask);
+        PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
 }
 
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void) {
-        paravirt_ops.io_delay();
+        pv_cpu_ops.io_delay();
 #ifdef REALLY_SLOW_IO
-        paravirt_ops.io_delay();
-        paravirt_ops.io_delay();
-        paravirt_ops.io_delay();
+        pv_cpu_ops.io_delay();
+        pv_cpu_ops.io_delay();
+        pv_cpu_ops.io_delay();
 #endif
 }
 
@@ -655,121 +692,120 @@ static inline void slow_down_io(void) {
  */
 static inline void apic_write(unsigned long reg, unsigned long v)
 {
-        PVOP_VCALL2(apic_write, reg, v);
+        PVOP_VCALL2(pv_apic_ops.apic_write, reg, v);
 }
 
 static inline void apic_write_atomic(unsigned long reg, unsigned long v)
 {
-        PVOP_VCALL2(apic_write_atomic, reg, v);
+        PVOP_VCALL2(pv_apic_ops.apic_write_atomic, reg, v);
 }
 
 static inline unsigned long apic_read(unsigned long reg)
 {
-        return PVOP_CALL1(unsigned long, apic_read, reg);
+        return PVOP_CALL1(unsigned long, pv_apic_ops.apic_read, reg);
 }
 
 static inline void setup_boot_clock(void)
 {
-        PVOP_VCALL0(setup_boot_clock);
+        PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
 }
 
 static inline void setup_secondary_clock(void)
 {
-        PVOP_VCALL0(setup_secondary_clock);
+        PVOP_VCALL0(pv_apic_ops.setup_secondary_clock);
 }
 #endif
 
 static inline void paravirt_post_allocator_init(void)
 {
-        if (paravirt_ops.post_allocator_init)
-                (*paravirt_ops.post_allocator_init)();
+        if (pv_init_ops.post_allocator_init)
+                (*pv_init_ops.post_allocator_init)();
 }
 
 static inline void paravirt_pagetable_setup_start(pgd_t *base)
 {
-        if (paravirt_ops.pagetable_setup_start)
-                (*paravirt_ops.pagetable_setup_start)(base);
+        (*pv_mmu_ops.pagetable_setup_start)(base);
 }
 
 static inline void paravirt_pagetable_setup_done(pgd_t *base)
 {
-        if (paravirt_ops.pagetable_setup_done)
-                (*paravirt_ops.pagetable_setup_done)(base);
+        (*pv_mmu_ops.pagetable_setup_done)(base);
 }
 
 #ifdef CONFIG_SMP
 static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
                                     unsigned long start_esp)
 {
-        PVOP_VCALL3(startup_ipi_hook, phys_apicid, start_eip, start_esp);
+        PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
+                    phys_apicid, start_eip, start_esp);
 }
 #endif
 
 static inline void paravirt_activate_mm(struct mm_struct *prev,
                                         struct mm_struct *next)
 {
-        PVOP_VCALL2(activate_mm, prev, next);
+        PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
 }
 
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
                                  struct mm_struct *mm)
 {
-        PVOP_VCALL2(dup_mmap, oldmm, mm);
+        PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
-        PVOP_VCALL1(exit_mmap, mm);
+        PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
 }
 
 static inline void __flush_tlb(void)
 {
-        PVOP_VCALL0(flush_tlb_user);
+        PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
 }
 static inline void __flush_tlb_global(void)
 {
-        PVOP_VCALL0(flush_tlb_kernel);
+        PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
 }
 static inline void __flush_tlb_single(unsigned long addr)
 {
-        PVOP_VCALL1(flush_tlb_single, addr);
+        PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
 }
 
 static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
                                     unsigned long va)
 {
-        PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va);
+        PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
 static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn)
 {
-        PVOP_VCALL2(alloc_pt, mm, pfn);
+        PVOP_VCALL2(pv_mmu_ops.alloc_pt, mm, pfn);
 }
 static inline void paravirt_release_pt(unsigned pfn)
 {
-        PVOP_VCALL1(release_pt, pfn);
+        PVOP_VCALL1(pv_mmu_ops.release_pt, pfn);
 }
 
 static inline void paravirt_alloc_pd(unsigned pfn)
 {
-        PVOP_VCALL1(alloc_pd, pfn);
+        PVOP_VCALL1(pv_mmu_ops.alloc_pd, pfn);
 }
 
 static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn,
                                            unsigned start, unsigned count)
 {
-        PVOP_VCALL4(alloc_pd_clone, pfn, clonepfn, start, count);
+        PVOP_VCALL4(pv_mmu_ops.alloc_pd_clone, pfn, clonepfn, start, count);
 }
 static inline void paravirt_release_pd(unsigned pfn)
 {
-        PVOP_VCALL1(release_pd, pfn);
+        PVOP_VCALL1(pv_mmu_ops.release_pd, pfn);
 }
 
 #ifdef CONFIG_HIGHPTE
 static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
 {
         unsigned long ret;
-        ret = PVOP_CALL2(unsigned long, kmap_atomic_pte, page, type);
+        ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type);
         return (void *)ret;
 }
 #endif
@@ -777,162 +813,191 @@ static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
 static inline void pte_update(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep)
 {
-        PVOP_VCALL3(pte_update, mm, addr, ptep);
+        PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
 }
 
 static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
                                     pte_t *ptep)
 {
-        PVOP_VCALL3(pte_update_defer, mm, addr, ptep);
+        PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
 }
 
 #ifdef CONFIG_X86_PAE
 static inline pte_t __pte(unsigned long long val)
 {
-        unsigned long long ret = PVOP_CALL2(unsigned long long, make_pte,
+        unsigned long long ret = PVOP_CALL2(unsigned long long,
+                                            pv_mmu_ops.make_pte,
                                             val, val >> 32);
         return (pte_t) { ret, ret >> 32 };
 }
 
 static inline pmd_t __pmd(unsigned long long val)
 {
-        return (pmd_t) { PVOP_CALL2(unsigned long long, make_pmd, val, val >> 32) };
+        return (pmd_t) { PVOP_CALL2(unsigned long long, pv_mmu_ops.make_pmd,
+                                    val, val >> 32) };
 }
 
 static inline pgd_t __pgd(unsigned long long val)
 {
-        return (pgd_t) { PVOP_CALL2(unsigned long long, make_pgd, val, val >> 32) };
+        return (pgd_t) { PVOP_CALL2(unsigned long long, pv_mmu_ops.make_pgd,
+                                    val, val >> 32) };
 }
 
 static inline unsigned long long pte_val(pte_t x)
 {
-        return PVOP_CALL2(unsigned long long, pte_val, x.pte_low, x.pte_high);
+        return PVOP_CALL2(unsigned long long, pv_mmu_ops.pte_val,
+                          x.pte_low, x.pte_high);
 }
 
 static inline unsigned long long pmd_val(pmd_t x)
 {
-        return PVOP_CALL2(unsigned long long, pmd_val, x.pmd, x.pmd >> 32);
+        return PVOP_CALL2(unsigned long long, pv_mmu_ops.pmd_val,
+                          x.pmd, x.pmd >> 32);
 }
 
 static inline unsigned long long pgd_val(pgd_t x)
 {
-        return PVOP_CALL2(unsigned long long, pgd_val, x.pgd, x.pgd >> 32);
+        return PVOP_CALL2(unsigned long long, pv_mmu_ops.pgd_val,
+                          x.pgd, x.pgd >> 32);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-        PVOP_VCALL3(set_pte, ptep, pteval.pte_low, pteval.pte_high);
+        PVOP_VCALL3(pv_mmu_ops.set_pte, ptep, pteval.pte_low, pteval.pte_high);
 }
 
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep, pte_t pteval)
 {
         /* 5 arg words */
-        paravirt_ops.set_pte_at(mm, addr, ptep, pteval);
+        pv_mmu_ops.set_pte_at(mm, addr, ptep, pteval);
 }
 
 static inline void set_pte_atomic(pte_t *ptep, pte_t pteval)
 {
-        PVOP_VCALL3(set_pte_atomic, ptep, pteval.pte_low, pteval.pte_high);
+        PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
+                    pteval.pte_low, pteval.pte_high);
 }
 
 static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
                                    pte_t *ptep, pte_t pte)
 {
         /* 5 arg words */
-        paravirt_ops.set_pte_present(mm, addr, ptep, pte);
+        pv_mmu_ops.set_pte_present(mm, addr, ptep, pte);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
-        PVOP_VCALL3(set_pmd, pmdp, pmdval.pmd, pmdval.pmd >> 32);
+        PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp,
+                    pmdval.pmd, pmdval.pmd >> 32);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pudval)
 {
-        PVOP_VCALL3(set_pud, pudp, pudval.pgd.pgd, pudval.pgd.pgd >> 32);
+        PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
+                    pudval.pgd.pgd, pudval.pgd.pgd >> 32);
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        PVOP_VCALL3(pte_clear, mm, addr, ptep);
+        PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-        PVOP_VCALL1(pmd_clear, pmdp);
+        PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
 }
 
 #else  /* !CONFIG_X86_PAE */
 
 static inline pte_t __pte(unsigned long val)
 {
-        return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) };
+        return (pte_t) { PVOP_CALL1(unsigned long, pv_mmu_ops.make_pte, val) };
 }
 
 static inline pgd_t __pgd(unsigned long val)
 {
-        return (pgd_t) { PVOP_CALL1(unsigned long, make_pgd, val) };
+        return (pgd_t) { PVOP_CALL1(unsigned long, pv_mmu_ops.make_pgd, val) };
 }
 
 static inline unsigned long pte_val(pte_t x)
 {
-        return PVOP_CALL1(unsigned long, pte_val, x.pte_low);
+        return PVOP_CALL1(unsigned long, pv_mmu_ops.pte_val, x.pte_low);
 }
 
 static inline unsigned long pgd_val(pgd_t x)
 {
-        return PVOP_CALL1(unsigned long, pgd_val, x.pgd);
+        return PVOP_CALL1(unsigned long, pv_mmu_ops.pgd_val, x.pgd);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-        PVOP_VCALL2(set_pte, ptep, pteval.pte_low);
+        PVOP_VCALL2(pv_mmu_ops.set_pte, ptep, pteval.pte_low);
 }
 
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep, pte_t pteval)
 {
-        PVOP_VCALL4(set_pte_at, mm, addr, ptep, pteval.pte_low);
+        PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pteval.pte_low);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
-        PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd);
+        PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, pmdval.pud.pgd.pgd);
 }
 #endif  /* CONFIG_X86_PAE */
 
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+        PARAVIRT_LAZY_NONE,
+        PARAVIRT_LAZY_MMU,
+        PARAVIRT_LAZY_CPU,
+};
+
+enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
+void paravirt_enter_lazy_cpu(void);
+void paravirt_leave_lazy_cpu(void);
+void paravirt_enter_lazy_mmu(void);
+void paravirt_leave_lazy_mmu(void);
+void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
+
 #define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
 static inline void arch_enter_lazy_cpu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_CPU);
+        PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
 }
 
 static inline void arch_leave_lazy_cpu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+        PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
 }
 
 static inline void arch_flush_lazy_cpu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+        if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
+                arch_leave_lazy_cpu_mode();
+                arch_enter_lazy_cpu_mode();
+        }
 }
 
 
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_MMU);
+        PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
 }
 
 static inline void arch_leave_lazy_mmu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+        PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
 static inline void arch_flush_lazy_mmu_mode(void)
 {
-        PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+        if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
+                arch_leave_lazy_mmu_mode();
+                arch_enter_lazy_mmu_mode();
+        }
 }
 
 void _paravirt_nop(void);
@@ -957,7 +1022,7 @@ static inline unsigned long __raw_local_save_flags(void)
                                   PARAVIRT_CALL
                                   "popl %%edx; popl %%ecx")
                      : "=a"(f)
-                     : paravirt_type(save_fl),
+                     : paravirt_type(pv_irq_ops.save_fl),
                        paravirt_clobber(CLBR_EAX)
                      : "memory", "cc");
         return f;
@@ -970,7 +1035,7 @@ static inline void raw_local_irq_restore(unsigned long f)
                                   "popl %%edx; popl %%ecx")
                      : "=a"(f)
                      : "0"(f),
-                       paravirt_type(restore_fl),
+                       paravirt_type(pv_irq_ops.restore_fl),
                        paravirt_clobber(CLBR_EAX)
                      : "memory", "cc");
 }
@@ -981,7 +1046,7 @@ static inline void raw_local_irq_disable(void)
                                   PARAVIRT_CALL
                                   "popl %%edx; popl %%ecx")
                      :
-                     : paravirt_type(irq_disable),
+                     : paravirt_type(pv_irq_ops.irq_disable),
                        paravirt_clobber(CLBR_EAX)
                      : "memory", "eax", "cc");
 }
@@ -992,7 +1057,7 @@ static inline void raw_local_irq_enable(void)
                                   PARAVIRT_CALL
                                   "popl %%edx; popl %%ecx")
                      :
-                     : paravirt_type(irq_enable),
+                     : paravirt_type(pv_irq_ops.irq_enable),
                        paravirt_clobber(CLBR_EAX)
                      : "memory", "eax", "cc");
 }
@@ -1008,21 +1073,23 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #define CLI_STRING                                                      \
         _paravirt_alt("pushl %%ecx; pushl %%edx;"                       \
-                      "call *paravirt_ops+%c[paravirt_cli_type]*4;"     \
+                      "call *%[paravirt_cli_opptr];"                    \
                       "popl %%edx; popl %%ecx",                         \
                       "%c[paravirt_cli_type]", "%c[paravirt_clobber]")
 
 #define STI_STRING                                                      \
         _paravirt_alt("pushl %%ecx; pushl %%edx;"                       \
-                      "call *paravirt_ops+%c[paravirt_sti_type]*4;"     \
+                      "call *%[paravirt_sti_opptr];"                    \
                       "popl %%edx; popl %%ecx",                         \
                       "%c[paravirt_sti_type]", "%c[paravirt_clobber]")
 
 #define CLI_STI_CLOBBERS , "%eax"
 #define CLI_STI_INPUT_ARGS                                              \
         ,                                                               \
-        [paravirt_cli_type] "i" (PARAVIRT_PATCH(irq_disable)),          \
-        [paravirt_sti_type] "i" (PARAVIRT_PATCH(irq_enable)),           \
+        [paravirt_cli_type] "i" (PARAVIRT_PATCH(pv_irq_ops.irq_disable)),               \
+        [paravirt_cli_opptr] "m" (pv_irq_ops.irq_disable),              \
+        [paravirt_sti_type] "i" (PARAVIRT_PATCH(pv_irq_ops.irq_enable)),                \
+        [paravirt_sti_opptr] "m" (pv_irq_ops.irq_enable),               \
         paravirt_clobber(CLBR_EAX)
 
 /* Make sure as little as possible of this mess escapes. */
@@ -1042,7 +1109,7 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #else  /* __ASSEMBLY__ */
 
-#define PARA_PATCH(off) ((off) / 4)
+#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4)
 
 #define PARA_SITE(ptype, clobbers, ops)         \
 771:;                                           \
@@ -1055,29 +1122,29 @@ static inline unsigned long __raw_local_irq_save(void)
          .short clobbers;                       \
         .popsection
 
-#define INTERRUPT_RETURN                                        \
-        PARA_SITE(PARA_PATCH(PARAVIRT_iret), CLBR_NONE,         \
-                  jmp *%cs:paravirt_ops+PARAVIRT_iret)
+#define INTERRUPT_RETURN                                                \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,       \
+                  jmp *%cs:pv_cpu_ops+PV_CPU_iret)
 
 #define DISABLE_INTERRUPTS(clobbers)                                    \
-        PARA_SITE(PARA_PATCH(PARAVIRT_irq_disable), clobbers,           \
+        PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
                   pushl %eax; pushl %ecx; pushl %edx;                   \
-                  call *%cs:paravirt_ops+PARAVIRT_irq_disable;          \
+                  call *%cs:pv_irq_ops+PV_IRQ_irq_disable;              \
                   popl %edx; popl %ecx; popl %eax)                      \
 
 #define ENABLE_INTERRUPTS(clobbers)                                     \
-        PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable), clobbers,            \
+        PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,  \
                   pushl %eax; pushl %ecx; pushl %edx;                   \
-                  call *%cs:paravirt_ops+PARAVIRT_irq_enable;           \
+                  call *%cs:pv_irq_ops+PV_IRQ_irq_enable;               \
                   popl %edx; popl %ecx; popl %eax)
 
-#define ENABLE_INTERRUPTS_SYSEXIT                                       \
-        PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable_sysexit), CLBR_NONE,   \
-                  jmp *%cs:paravirt_ops+PARAVIRT_irq_enable_sysexit)
+#define ENABLE_INTERRUPTS_SYSEXIT                                              \
+        PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), CLBR_NONE,\
+                  jmp *%cs:pv_cpu_ops+PV_CPU_irq_enable_sysexit)
 
 #define GET_CR0_INTO_EAX                        \
         push %ecx; push %edx;                   \
-        call *paravirt_ops+PARAVIRT_read_cr0;   \
+        call *pv_cpu_ops+PV_CPU_read_cr0;       \
         pop %edx; pop %ecx
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/asm-x86/parport.h b/include/asm-x86/parport.h
index 2a31157349c9..019cbca24a38 100644
--- a/include/asm-x86/parport.h
+++ b/include/asm-x86/parport.h
@@ -1,5 +1,10 @@
-#ifdef CONFIG_X86_32
-# include "parport_32.h"
-#else
-# include "parport_64.h"
-#endif
+#ifndef _ASM_X86_PARPORT_H
+#define _ASM_X86_PARPORT_H
+
+static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+        return parport_pc_find_isa_ports (autoirq, autodma);
+}
+
+#endif /* _ASM_X86_PARPORT_H */
diff --git a/include/asm-x86/parport_32.h b/include/asm-x86/parport_32.h
deleted file mode 100644
index fa0e321e498e..000000000000
--- a/include/asm-x86/parport_32.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * parport.h: ia32-specific parport initialisation
- *
- * Copyright (C) 1999, 2000  Tim Waugh <tim@cyberelk.demon.co.uk>
- *
- * This file should only be included by drivers/parport/parport_pc.c.
- */
-
-#ifndef _ASM_I386_PARPORT_H
-#define _ASM_I386_PARPORT_H 1
-
-static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
-{
-        return parport_pc_find_isa_ports (autoirq, autodma);
-}
-
-#endif /* !(_ASM_I386_PARPORT_H) */
diff --git a/include/asm-x86/parport_64.h b/include/asm-x86/parport_64.h
deleted file mode 100644
index 7135ef977c96..000000000000
--- a/include/asm-x86/parport_64.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * parport.h: ia32-specific parport initialisation
- *
- * Copyright (C) 1999, 2000  Tim Waugh <tim@cyberelk.demon.co.uk>
- *
- * This file should only be included by drivers/parport/parport_pc.c.
- */
-
-#ifndef _ASM_X8664_PARPORT_H
-#define _ASM_X8664_PARPORT_H 1
-
-static int __devinit parport_pc_find_isa_ports (int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
-{
-        return parport_pc_find_isa_ports (autoirq, autodma);
-}
-
-#endif 
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
index fb49f80eb94f..35962bbe5e72 100644
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@ -30,6 +30,12 @@ struct x8664_pda {
         struct mm_struct *active_mm;
         unsigned apic_timer_irqs;
         unsigned irq0_irqs;
+        unsigned irq_resched_count;
+        unsigned irq_call_count;
+        unsigned irq_tlb_count;
+        unsigned irq_thermal_count;
+        unsigned irq_threshold_count;
+        unsigned irq_spurious_count;
 } ____cacheline_aligned_in_smp;
 
 extern struct x8664_pda *_cpu_pda[];
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
index c0df89f66e8b..448ac9516314 100644
--- a/include/asm-x86/pgtable-3level-defs.h
+++ b/include/asm-x86/pgtable-3level-defs.h
@@ -2,7 +2,7 @@
 #define _I386_PGTABLE_3LEVEL_DEFS_H
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD       (paravirt_ops.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD       (pv_info.shared_kernel_pmd)
 #else
 #define SHARED_KERNEL_PMD       1
 #endif
diff --git a/include/asm-x86/processor_32.h b/include/asm-x86/processor_32.h
index 3845fe72383e..83800e7496ee 100644
--- a/include/asm-x86/processor_32.h
+++ b/include/asm-x86/processor_32.h
@@ -595,7 +595,9 @@ static inline void load_esp0(struct tss_struct *tss, struct thread_struct *threa
  * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
  * resulting in stale register contents being returned.
  */
-static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx)
+static inline void cpuid(unsigned int op,
+                         unsigned int *eax, unsigned int *ebx,
+                         unsigned int *ecx, unsigned int *edx)
 {
         *eax = op;
         *ecx = 0;
@@ -603,8 +605,9 @@ static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx,
 }
 
 /* Some CPUID calls want 'count' to be placed in ecx */
-static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx,
-                               int *edx)
+static inline void cpuid_count(unsigned int op, int count,
+                               unsigned int *eax, unsigned int *ebx,
+                               unsigned int *ecx, unsigned int *edx)
 {
         *eax = op;
         *ecx = count;
@@ -674,6 +677,17 @@ static inline unsigned int cpuid_edx(unsigned int op)
 #define K7_NOP7        ".byte 0x8D,0x04,0x05,0,0,0,0\n"
 #define K7_NOP8        K7_NOP7 ASM_NOP1
 
+/* P6 nops */
+/* uses eax dependencies (Intel-recommended choice) */
+#define P6_NOP1 GENERIC_NOP1
+#define P6_NOP2 ".byte 0x66,0x90\n"
+#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
+#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
+#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
+#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+
 #ifdef CONFIG_MK8
 #define ASM_NOP1 K8_NOP1
 #define ASM_NOP2 K8_NOP2
@@ -692,6 +706,17 @@ static inline unsigned int cpuid_edx(unsigned int op)
 #define ASM_NOP6 K7_NOP6
 #define ASM_NOP7 K7_NOP7
 #define ASM_NOP8 K7_NOP8
+#elif defined(CONFIG_M686) || defined(CONFIG_MPENTIUMII) || \
+      defined(CONFIG_MPENTIUMIII) || defined(CONFIG_MPENTIUMM) || \
+      defined(CONFIG_MCORE2) || defined(CONFIG_PENTIUM4)
+#define ASM_NOP1 P6_NOP1
+#define ASM_NOP2 P6_NOP2
+#define ASM_NOP3 P6_NOP3
+#define ASM_NOP4 P6_NOP4
+#define ASM_NOP5 P6_NOP5
+#define ASM_NOP6 P6_NOP6
+#define ASM_NOP7 P6_NOP7
+#define ASM_NOP8 P6_NOP8
 #else
 #define ASM_NOP1 GENERIC_NOP1
 #define ASM_NOP2 GENERIC_NOP2
diff --git a/include/asm-x86/processor_64.h b/include/asm-x86/processor_64.h
index 31f579b828f2..f422becbddd9 100644
--- a/include/asm-x86/processor_64.h
+++ b/include/asm-x86/processor_64.h
@@ -334,6 +334,16 @@ struct extended_sigtable {
 };
 
 
+#if defined(CONFIG_MPSC) || defined(CONFIG_MCORE2)
+#define ASM_NOP1 P6_NOP1
+#define ASM_NOP2 P6_NOP2
+#define ASM_NOP3 P6_NOP3
+#define ASM_NOP4 P6_NOP4
+#define ASM_NOP5 P6_NOP5
+#define ASM_NOP6 P6_NOP6
+#define ASM_NOP7 P6_NOP7
+#define ASM_NOP8 P6_NOP8
+#else
 #define ASM_NOP1 K8_NOP1
 #define ASM_NOP2 K8_NOP2
 #define ASM_NOP3 K8_NOP3
@@ -342,6 +352,7 @@ struct extended_sigtable {
 #define ASM_NOP6 K8_NOP6
 #define ASM_NOP7 K8_NOP7
 #define ASM_NOP8 K8_NOP8
+#endif
 
 /* Opteron nops */
 #define K8_NOP1 ".byte 0x90\n"
@@ -353,6 +364,17 @@ struct extended_sigtable {
 #define K8_NOP7 K8_NOP4 K8_NOP3
 #define K8_NOP8 K8_NOP4 K8_NOP4
 
+/* P6 nops */
+/* uses eax dependencies (Intel-recommended choice) */
+#define P6_NOP1 ".byte 0x90\n"
+#define P6_NOP2 ".byte 0x66,0x90\n"
+#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
+#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
+#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
+#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+
 #define ASM_NOP_MAX 8
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
@@ -389,11 +411,6 @@ static inline void prefetchw(void *x)
 
 #define cpu_relax()   rep_nop()
 
-static inline void serialize_cpu(void)
-{
-        __asm__ __volatile__ ("cpuid" : : : "ax", "bx", "cx", "dx");
-}
-
 static inline void __monitor(const void *eax, unsigned long ecx,
                 unsigned long edx)
 {
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
index 6824c49def1c..7524e1233833 100644
--- a/include/asm-x86/ptrace-abi.h
+++ b/include/asm-x86/ptrace-abi.h
@@ -1,13 +1,81 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "ptrace-abi_32.h"
-# else
-#  include "ptrace-abi_64.h"
-# endif
+#ifndef _ASM_X86_PTRACE_ABI_H
+#define _ASM_X86_PTRACE_ABI_H
+
+#ifdef __i386__
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS  13
+#define EFL 14
+#define UESP 15
+#define SS   16
+#define FRAME_SIZE 17
+
+#else /* __i386__ */
+
+#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11 48
+#define R10 56
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120       /* = ERROR */
+/* end of arguments */
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
+#define ARGOFFSET R11
+#endif /* __ASSEMBLY__ */
+
+/* top of stack page */
+#define FRAME_SIZE 168
+
+#endif /* !__i386__ */
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS            12
+#define PTRACE_SETREGS            13
+#define PTRACE_GETFPREGS          14
+#define PTRACE_SETFPREGS          15
+#define PTRACE_GETFPXREGS         18
+#define PTRACE_SETFPXREGS         19
+
+#define PTRACE_OLDSETOPTIONS      21
+
+/* only useful for access 32bit programs / kernels */
+#define PTRACE_GET_THREAD_AREA    25
+#define PTRACE_SET_THREAD_AREA    26
+
+#ifdef __x86_64__
+# define PTRACE_ARCH_PRCTL        30
 #else
-# ifdef __i386__
-#  include "ptrace-abi_32.h"
-# else
-#  include "ptrace-abi_64.h"
-# endif
+# define PTRACE_SYSEMU            31
+# define PTRACE_SYSEMU_SINGLESTEP 32
+#endif
+
 #endif
diff --git a/include/asm-x86/ptrace-abi_32.h b/include/asm-x86/ptrace-abi_32.h
deleted file mode 100644
index a44901817a26..000000000000
--- a/include/asm-x86/ptrace-abi_32.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef I386_PTRACE_ABI_H
-#define I386_PTRACE_ABI_H
-
-#define EBX 0
-#define ECX 1
-#define EDX 2
-#define ESI 3
-#define EDI 4
-#define EBP 5
-#define EAX 6
-#define DS 7
-#define ES 8
-#define FS 9
-#define GS 10
-#define ORIG_EAX 11
-#define EIP 12
-#define CS  13
-#define EFL 14
-#define UESP 15
-#define SS   16
-#define FRAME_SIZE 17
-
-/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
-#define PTRACE_GETREGS            12
-#define PTRACE_SETREGS            13
-#define PTRACE_GETFPREGS          14
-#define PTRACE_SETFPREGS          15
-#define PTRACE_GETFPXREGS         18
-#define PTRACE_SETFPXREGS         19
-
-#define PTRACE_OLDSETOPTIONS         21
-
-#define PTRACE_GET_THREAD_AREA    25
-#define PTRACE_SET_THREAD_AREA    26
-
-#define PTRACE_SYSEMU             31
-#define PTRACE_SYSEMU_SINGLESTEP  32
-
-#endif
diff --git a/include/asm-x86/ptrace-abi_64.h b/include/asm-x86/ptrace-abi_64.h
deleted file mode 100644
index 19184b0806b1..000000000000
--- a/include/asm-x86/ptrace-abi_64.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _X86_64_PTRACE_ABI_H
-#define _X86_64_PTRACE_ABI_H
-
-#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
-#define R15 0
-#define R14 8
-#define R13 16
-#define R12 24
-#define RBP 32
-#define RBX 40
-/* arguments: interrupts/non tracing syscalls only save upto here*/
-#define R11 48
-#define R10 56
-#define R9 64
-#define R8 72
-#define RAX 80
-#define RCX 88
-#define RDX 96
-#define RSI 104
-#define RDI 112
-#define ORIG_RAX 120       /* = ERROR */
-/* end of arguments */
-/* cpu exception frame or undefined in case of fast syscall. */
-#define RIP 128
-#define CS 136
-#define EFLAGS 144
-#define RSP 152
-#define SS 160
-#define ARGOFFSET R11
-#endif /* __ASSEMBLY__ */
-
-/* top of stack page */
-#define FRAME_SIZE 168
-
-#define PTRACE_OLDSETOPTIONS         21
-
-/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
-#define PTRACE_GETREGS            12
-#define PTRACE_SETREGS            13
-#define PTRACE_GETFPREGS          14
-#define PTRACE_SETFPREGS          15
-#define PTRACE_GETFPXREGS         18
-#define PTRACE_SETFPXREGS         19
-
-/* only useful for access 32bit programs */
-#define PTRACE_GET_THREAD_AREA    25
-#define PTRACE_SET_THREAD_AREA    26
-
-#define PTRACE_ARCH_PRCTL         30    /* arch_prctl for child */
-
-#endif
diff --git a/include/asm-x86/resource.h b/include/asm-x86/resource.h
index 732410a8c02a..04bc4db8921b 100644
--- a/include/asm-x86/resource.h
+++ b/include/asm-x86/resource.h
@@ -1,13 +1 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "resource_32.h"
-# else
-#  include "resource_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "resource_32.h"
-# else
-#  include "resource_64.h"
-# endif
-#endif
+#include <asm-generic/resource.h>
diff --git a/include/asm-x86/resource_32.h b/include/asm-x86/resource_32.h
deleted file mode 100644
index 6c1ea37c7718..000000000000
--- a/include/asm-x86/resource_32.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _I386_RESOURCE_H
-#define _I386_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif
diff --git a/include/asm-x86/resource_64.h b/include/asm-x86/resource_64.h
deleted file mode 100644
index f40b40623234..000000000000
--- a/include/asm-x86/resource_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _X8664_RESOURCE_H
-#define _X8664_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif
diff --git a/include/asm-x86/rtc.h b/include/asm-x86/rtc.h
index 1f0c98eb2e38..f71c3b0ed360 100644
--- a/include/asm-x86/rtc.h
+++ b/include/asm-x86/rtc.h
@@ -1,5 +1 @@
-#ifdef CONFIG_X86_32
-# include "rtc_32.h"
-#else
-# include "rtc_64.h"
-#endif
+#include <asm-generic/rtc.h>
diff --git a/include/asm-x86/rtc_32.h b/include/asm-x86/rtc_32.h
deleted file mode 100644
index ffd02109a0e5..000000000000
--- a/include/asm-x86/rtc_32.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _I386_RTC_H
-#define _I386_RTC_H
-
-/*
- * x86 uses the default access methods for the RTC.
- */
-
-#include <asm-generic/rtc.h>
-
-#endif
diff --git a/include/asm-x86/rtc_64.h b/include/asm-x86/rtc_64.h
deleted file mode 100644
index 18ed713ac7de..000000000000
--- a/include/asm-x86/rtc_64.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _X86_64_RTC_H
-#define _X86_64_RTC_H
-
-/*
- * x86 uses the default access methods for the RTC.
- */
-
-#include <asm-generic/rtc.h>
-
-#endif
diff --git a/include/asm-x86/rwlock.h b/include/asm-x86/rwlock.h
index a3be7d8364af..f2b64a429e6b 100644
--- a/include/asm-x86/rwlock.h
+++ b/include/asm-x86/rwlock.h
@@ -1,5 +1,9 @@
-#ifdef CONFIG_X86_32
-# include "rwlock_32.h"
-#else
-# include "rwlock_64.h"
-#endif
+#ifndef _ASM_X86_RWLOCK_H
+#define _ASM_X86_RWLOCK_H
+
+#define RW_LOCK_BIAS             0x01000000
+#define RW_LOCK_BIAS_STR        "0x01000000"
+
+/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
+
+#endif /* _ASM_X86_RWLOCK_H */
diff --git a/include/asm-x86/rwlock_32.h b/include/asm-x86/rwlock_32.h
deleted file mode 100644
index c3e5db32fa48..000000000000
--- a/include/asm-x86/rwlock_32.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* include/asm-i386/rwlock.h
- *
- *      Helpers used by both rw spinlocks and rw semaphores.
- *
- *      Based in part on code from semaphore.h and
- *      spinlock.h Copyright 1996 Linus Torvalds.
- *
- *      Copyright 1999 Red Hat, Inc.
- *
- *      Written by Benjamin LaHaise.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-#ifndef _ASM_I386_RWLOCK_H
-#define _ASM_I386_RWLOCK_H
-
-#define RW_LOCK_BIAS             0x01000000
-#define RW_LOCK_BIAS_STR        "0x01000000"
-
-/* Code is in asm-i386/spinlock.h */
-
-#endif
diff --git a/include/asm-x86/rwlock_64.h b/include/asm-x86/rwlock_64.h
deleted file mode 100644
index 72aeebed920b..000000000000
--- a/include/asm-x86/rwlock_64.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* include/asm-x86_64/rwlock.h
- *
- *      Helpers used by both rw spinlocks and rw semaphores.
- *
- *      Based in part on code from semaphore.h and
- *      spinlock.h Copyright 1996 Linus Torvalds.
- *
- *      Copyright 1999 Red Hat, Inc.
- *      Copyright 2001,2002 SuSE labs 
- *
- *      Written by Benjamin LaHaise.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-#ifndef _ASM_X86_64_RWLOCK_H
-#define _ASM_X86_64_RWLOCK_H
-
-#define RW_LOCK_BIAS             0x01000000
-#define RW_LOCK_BIAS_STR         "0x01000000"
-
-/* Actual code is in asm/spinlock.h or in arch/x86_64/lib/rwlock.S */
-
-#endif
diff --git a/include/asm-x86/sections.h b/include/asm-x86/sections.h
index ae6c69d9be3f..2b8c5160388f 100644
--- a/include/asm-x86/sections.h
+++ b/include/asm-x86/sections.h
@@ -1,5 +1 @@
-#ifdef CONFIG_X86_32
-# include "sections_32.h"
-#else
-# include "sections_64.h"
-#endif
+#include <asm-generic/sections.h>
diff --git a/include/asm-x86/sections_32.h b/include/asm-x86/sections_32.h
deleted file mode 100644
index 2dcbb92918b2..000000000000
--- a/include/asm-x86/sections_32.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _I386_SECTIONS_H
-#define _I386_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/include/asm-x86/sections_64.h b/include/asm-x86/sections_64.h
deleted file mode 100644
index c746d9f1e70c..000000000000
--- a/include/asm-x86/sections_64.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _X8664_SECTIONS_H
-#define _X8664_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/include/asm-x86/sembuf.h b/include/asm-x86/sembuf.h
index e42c971e383f..ee50c801f7b7 100644
--- a/include/asm-x86/sembuf.h
+++ b/include/asm-x86/sembuf.h
@@ -1,13 +1,24 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "sembuf_32.h"
-# else
-#  include "sembuf_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "sembuf_32.h"
-# else
-#  include "sembuf_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_SEMBUF_H
+#define _ASM_X86_SEMBUF_H
+
+/*
+ * The semid64_ds structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+struct semid64_ds {
+        struct ipc64_perm sem_perm;     /* permissions .. see ipc.h */
+        __kernel_time_t sem_otime;      /* last semop time */
+        unsigned long   __unused1;
+        __kernel_time_t sem_ctime;      /* last change time */
+        unsigned long   __unused2;
+        unsigned long   sem_nsems;      /* no. of semaphores in array */
+        unsigned long   __unused3;
+        unsigned long   __unused4;
+};
+
+#endif /* _ASM_X86_SEMBUF_H */
diff --git a/include/asm-x86/sembuf_32.h b/include/asm-x86/sembuf_32.h
deleted file mode 100644
index 323835166c14..000000000000
--- a/include/asm-x86/sembuf_32.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _I386_SEMBUF_H
-#define _I386_SEMBUF_H
-
-/* 
- * The semid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-        struct ipc64_perm sem_perm;             /* permissions .. see ipc.h */
-        __kernel_time_t sem_otime;              /* last semop time */
-        unsigned long   __unused1;
-        __kernel_time_t sem_ctime;              /* last change time */
-        unsigned long   __unused2;
-        unsigned long   sem_nsems;              /* no. of semaphores in array */
-        unsigned long   __unused3;
-        unsigned long   __unused4;
-};
-
-#endif /* _I386_SEMBUF_H */
diff --git a/include/asm-x86/sembuf_64.h b/include/asm-x86/sembuf_64.h
deleted file mode 100644
index 63b52925ae2a..000000000000
--- a/include/asm-x86/sembuf_64.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _X86_64_SEMBUF_H
-#define _X86_64_SEMBUF_H
-
-/* 
- * The semid64_ds structure for x86_64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-        struct ipc64_perm sem_perm;             /* permissions .. see ipc.h */
-        __kernel_time_t sem_otime;              /* last semop time */
-        unsigned long   __unused1;
-        __kernel_time_t sem_ctime;              /* last change time */
-        unsigned long   __unused2;
-        unsigned long   sem_nsems;              /* no. of semaphores in array */
-        unsigned long   __unused3;
-        unsigned long   __unused4;
-};
-
-#endif /* _X86_64_SEMBUF_H */
diff --git a/include/asm-x86/serial.h b/include/asm-x86/serial.h
index cf1b05227b29..628c801535ea 100644
--- a/include/asm-x86/serial.h
+++ b/include/asm-x86/serial.h
@@ -1,5 +1,29 @@
-#ifdef CONFIG_X86_32
-# include "serial_32.h"
+#ifndef _ASM_X86_SERIAL_H
+#define _ASM_X86_SERIAL_H
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
 #else
-# include "serial_64.h"
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
 #endif
+
+#define SERIAL_PORT_DFNS                        \
+        /* UART CLK   PORT IRQ     FLAGS        */                      \
+        { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },      /* ttyS0 */     \
+        { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },      /* ttyS1 */     \
+        { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
+        { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
+
+#endif /* _ASM_X86_SERIAL_H */
diff --git a/include/asm-x86/serial_32.h b/include/asm-x86/serial_32.h
deleted file mode 100644
index bd67480ca109..000000000000
--- a/include/asm-x86/serial_32.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * include/asm-i386/serial.h
- */
-
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD ( 1843200 / 16 )
-
-/* Standard COM flags (except for COM4, because of the 8514 problem) */
-#ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
-#else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
-#endif
-
-#define SERIAL_PORT_DFNS                        \
-        /* UART CLK   PORT IRQ     FLAGS        */                      \
-        { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },      /* ttyS0 */     \
-        { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },      /* ttyS1 */     \
-        { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
-        { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
diff --git a/include/asm-x86/serial_64.h b/include/asm-x86/serial_64.h
deleted file mode 100644
index b0496e0d72a6..000000000000
--- a/include/asm-x86/serial_64.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * include/asm-x86_64/serial.h
- */
-
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD ( 1843200 / 16 )
-
-/* Standard COM flags (except for COM4, because of the 8514 problem) */
-#ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
-#else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
-#endif
-
-#define SERIAL_PORT_DFNS                        \
-        /* UART CLK   PORT IRQ     FLAGS        */                      \
-        { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },      /* ttyS0 */     \
-        { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },      /* ttyS1 */     \
-        { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },      /* ttyS2 */     \
-        { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },     /* ttyS3 */
diff --git a/include/asm-x86/shmparam.h b/include/asm-x86/shmparam.h
index 165627cc5345..0880cf0917b9 100644
--- a/include/asm-x86/shmparam.h
+++ b/include/asm-x86/shmparam.h
@@ -1,13 +1,6 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "shmparam_32.h"
-# else
-#  include "shmparam_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "shmparam_32.h"
-# else
-#  include "shmparam_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_SHMPARAM_H
+#define _ASM_X86_SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE         /* attach addr a multiple of this */
+
+#endif /* _ASM_X86_SHMPARAM_H */
diff --git a/include/asm-x86/shmparam_32.h b/include/asm-x86/shmparam_32.h
deleted file mode 100644
index 786243a5b319..000000000000
--- a/include/asm-x86/shmparam_32.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASMI386_SHMPARAM_H
-#define _ASMI386_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
-
-#endif /* _ASMI386_SHMPARAM_H */
diff --git a/include/asm-x86/shmparam_64.h b/include/asm-x86/shmparam_64.h
deleted file mode 100644
index d7021620dcb7..000000000000
--- a/include/asm-x86/shmparam_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASMX8664_SHMPARAM_H
-#define _ASMX8664_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
-
-#endif /* _ASMX8664_SHMPARAM_H */
diff --git a/include/asm-x86/siginfo.h b/include/asm-x86/siginfo.h
index 0b8e4bb47d25..a477bea0c2a1 100644
--- a/include/asm-x86/siginfo.h
+++ b/include/asm-x86/siginfo.h
@@ -1,13 +1,10 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "siginfo_32.h"
-# else
-#  include "siginfo_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "siginfo_32.h"
-# else
-#  include "siginfo_64.h"
-# endif
+#ifndef _ASM_X86_SIGINFO_H
+#define _ASM_X86_SIGINFO_H
+
+#ifdef __x86_64__
+# define __ARCH_SI_PREAMBLE_SIZE        (4 * sizeof(int))
+#endif
+
+#include <asm-generic/siginfo.h>
+
 #endif
diff --git a/include/asm-x86/siginfo_32.h b/include/asm-x86/siginfo_32.h
deleted file mode 100644
index fe18f98fccfa..000000000000
--- a/include/asm-x86/siginfo_32.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _I386_SIGINFO_H
-#define _I386_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-#endif
diff --git a/include/asm-x86/siginfo_64.h b/include/asm-x86/siginfo_64.h
deleted file mode 100644
index d09a1e6e7246..000000000000
--- a/include/asm-x86/siginfo_64.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _X8664_SIGINFO_H
-#define _X8664_SIGINFO_H
-
-#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
-
-#include <asm-generic/siginfo.h>
-
-#endif
diff --git a/include/asm-x86/smp_32.h b/include/asm-x86/smp_32.h
index 955dd7c8538f..ee46038d126c 100644
--- a/include/asm-x86/smp_32.h
+++ b/include/asm-x86/smp_32.h
@@ -92,12 +92,9 @@ static inline void smp_send_reschedule(int cpu)
 {
         smp_ops.smp_send_reschedule(cpu);
 }
-static inline int smp_call_function_mask(cpumask_t mask,
-                                         void (*func) (void *info), void *info,
-                                         int wait)
-{
-        return smp_ops.smp_call_function_mask(mask, func, info, wait);
-}
+extern int smp_call_function_mask(cpumask_t mask,
+                                  void (*func) (void *info), void *info,
+                                  int wait);
 
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
diff --git a/include/asm-x86/smp_64.h b/include/asm-x86/smp_64.h
index f5bcee1c0927..d30e9b684fdd 100644
--- a/include/asm-x86/smp_64.h
+++ b/include/asm-x86/smp_64.h
@@ -85,7 +85,6 @@ static inline int hard_smp_processor_id(void)
  * the real APIC ID <-> CPU # mapping.
  */
 extern u8 x86_cpu_to_apicid[NR_CPUS];   /* physical ID */
-extern u8 x86_cpu_to_log_apicid[NR_CPUS];
 extern u8 bios_cpu_apicid[];
 
 static inline int cpu_present_to_apicid(int mps_cpu)
diff --git a/include/asm-x86/sockios.h b/include/asm-x86/sockios.h
index 5a134fc70b9c..49cc72b5d3c9 100644
--- a/include/asm-x86/sockios.h
+++ b/include/asm-x86/sockios.h
@@ -1,13 +1,13 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "sockios_32.h"
-# else
-#  include "sockios_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "sockios_32.h"
-# else
-#  include "sockios_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_SOCKIOS_H
+#define _ASM_X86_SOCKIOS_H
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN       0x8901
+#define SIOCSPGRP       0x8902
+#define FIOGETOWN       0x8903
+#define SIOCGPGRP       0x8904
+#define SIOCATMARK      0x8905
+#define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
+#define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
+
+#endif /* _ASM_X86_SOCKIOS_H */
diff --git a/include/asm-x86/sockios_32.h b/include/asm-x86/sockios_32.h
deleted file mode 100644
index ff528c7d255c..000000000000
--- a/include/asm-x86/sockios_32.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ARCH_I386_SOCKIOS__
-#define __ARCH_I386_SOCKIOS__
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN       0x8901
-#define SIOCSPGRP       0x8902
-#define FIOGETOWN       0x8903
-#define SIOCGPGRP       0x8904
-#define SIOCATMARK      0x8905
-#define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
-#define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
-
-#endif
diff --git a/include/asm-x86/sockios_64.h b/include/asm-x86/sockios_64.h
deleted file mode 100644
index d726ba2513e3..000000000000
--- a/include/asm-x86/sockios_64.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ARCH_X8664_SOCKIOS__
-#define __ARCH_X8664_SOCKIOS__
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN       0x8901
-#define SIOCSPGRP       0x8902
-#define FIOGETOWN       0x8903
-#define SIOCGPGRP       0x8904
-#define SIOCATMARK      0x8905
-#define SIOCGSTAMP      0x8906          /* Get stamp (timeval) */
-#define SIOCGSTAMPNS    0x8907          /* Get stamp (timespec) */
-
-#endif
diff --git a/include/asm-x86/stacktrace.h b/include/asm-x86/stacktrace.h
index 6f0b54594307..70dd5bae3235 100644
--- a/include/asm-x86/stacktrace.h
+++ b/include/asm-x86/stacktrace.h
@@ -15,6 +15,6 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack,
-                struct stacktrace_ops *ops, void *data);
+                const struct stacktrace_ops *ops, void *data);
 
 #endif
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
index a9b64453bdf5..55bfa308f900 100644
--- a/include/asm-x86/string_32.h
+++ b/include/asm-x86/string_32.h
@@ -26,9 +26,6 @@ extern int strncmp(const char *cs, const char *ct, size_t count);
 #define __HAVE_ARCH_STRCHR
 extern char *strchr(const char *s, int c);
 
-#define __HAVE_ARCH_STRRCHR
-extern char *strrchr(const char *s, int c);
-
 #define __HAVE_ARCH_STRLEN
 extern size_t strlen(const char *s);
 
diff --git a/include/asm-x86/system_32.h b/include/asm-x86/system_32.h
index d84e593b7dfc..db6283eb5e46 100644
--- a/include/asm-x86/system_32.h
+++ b/include/asm-x86/system_32.h
@@ -142,7 +142,7 @@ static inline unsigned long native_read_cr4_safe(void)
 {
         unsigned long val;
         /* This could fault if %cr4 does not exist */
-        asm("1: movl %%cr4, %0          \n"
+        asm volatile("1: movl %%cr4, %0         \n"
                 "2:                             \n"
                 ".section __ex_table,\"a\"      \n"
                 ".long 1b,2b                    \n"
@@ -161,6 +161,10 @@ static inline void native_wbinvd(void)
         asm volatile("wbinvd": : :"memory");
 }
 
+static inline void clflush(volatile void *__p)
+{
+        asm volatile("clflush %0" : "+m" (*(char __force *)__p));
+}
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/include/asm-x86/system_64.h b/include/asm-x86/system_64.h
index 5022aecc333d..4cb23848d460 100644
--- a/include/asm-x86/system_64.h
+++ b/include/asm-x86/system_64.h
@@ -7,9 +7,6 @@
 
 #ifdef __KERNEL__
 
-#define __STR(x) #x
-#define STR(x) __STR(x)
-
 #define __SAVE(reg,offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
 #define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
 
@@ -85,7 +82,7 @@ static inline void write_cr0(unsigned long val)
 static inline unsigned long read_cr2(void)
 {
         unsigned long cr2;
-        asm("movq %%cr2,%0" : "=r" (cr2));
+        asm volatile("movq %%cr2,%0" : "=r" (cr2));
         return cr2;
 }
 
@@ -97,7 +94,7 @@ static inline void write_cr2(unsigned long val)
 static inline unsigned long read_cr3(void)
 { 
         unsigned long cr3;
-        asm("movq %%cr3,%0" : "=r" (cr3));
+        asm volatile("movq %%cr3,%0" : "=r" (cr3));
         return cr3;
 }
 
@@ -109,7 +106,7 @@ static inline void write_cr3(unsigned long val)
 static inline unsigned long read_cr4(void)
 { 
         unsigned long cr4;
-        asm("movq %%cr4,%0" : "=r" (cr4));
+        asm volatile("movq %%cr4,%0" : "=r" (cr4));
         return cr4;
 }
 
@@ -121,7 +118,7 @@ static inline void write_cr4(unsigned long val)
 static inline unsigned long read_cr8(void)
 {
         unsigned long cr8;
-        asm("movq %%cr8,%0" : "=r" (cr8));
+        asm volatile("movq %%cr8,%0" : "=r" (cr8));
         return cr8;
 }
 
@@ -137,6 +134,11 @@ static inline void write_cr8(unsigned long val)
 
 #endif  /* __KERNEL__ */
 
+static inline void clflush(volatile void *__p)
+{
+        asm volatile("clflush %0" : "+m" (*(char __force *)__p));
+}
+
 #define nop() __asm__ __volatile__ ("nop")
 
 #ifdef CONFIG_SMP
diff --git a/include/asm-x86/termbits.h b/include/asm-x86/termbits.h
index 69f3080e2a1d..af1b70ea440f 100644
--- a/include/asm-x86/termbits.h
+++ b/include/asm-x86/termbits.h
@@ -1,13 +1,198 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "termbits_32.h"
-# else
-#  include "termbits_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "termbits_32.h"
-# else
-#  include "termbits_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_TERMBITS_H
+#define _ASM_X86_TERMBITS_H
+
+#include <linux/posix_types.h>
+
+typedef unsigned char   cc_t;
+typedef unsigned int    speed_t;
+typedef unsigned int    tcflag_t;
+
+#define NCCS 19
+struct termios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+};
+
+struct termios2 {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+struct ktermios {
+        tcflag_t c_iflag;               /* input mode flags */
+        tcflag_t c_oflag;               /* output mode flags */
+        tcflag_t c_cflag;               /* control mode flags */
+        tcflag_t c_lflag;               /* local mode flags */
+        cc_t c_line;                    /* line discipline */
+        cc_t c_cc[NCCS];                /* control characters */
+        speed_t c_ispeed;               /* input speed */
+        speed_t c_ospeed;               /* output speed */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK  0000001
+#define BRKINT  0000002
+#define IGNPAR  0000004
+#define PARMRK  0000010
+#define INPCK   0000020
+#define ISTRIP  0000040
+#define INLCR   0000100
+#define IGNCR   0000200
+#define ICRNL   0000400
+#define IUCLC   0001000
+#define IXON    0002000
+#define IXANY   0004000
+#define IXOFF   0010000
+#define IMAXBEL 0020000
+#define IUTF8   0040000
+
+/* c_oflag bits */
+#define OPOST   0000001
+#define OLCUC   0000002
+#define ONLCR   0000004
+#define OCRNL   0000010
+#define ONOCR   0000020
+#define ONLRET  0000040
+#define OFILL   0000100
+#define OFDEL   0000200
+#define NLDLY   0000400
+#define   NL0   0000000
+#define   NL1   0000400
+#define CRDLY   0003000
+#define   CR0   0000000
+#define   CR1   0001000
+#define   CR2   0002000
+#define   CR3   0003000
+#define TABDLY  0014000
+#define   TAB0  0000000
+#define   TAB1  0004000
+#define   TAB2  0010000
+#define   TAB3  0014000
+#define   XTABS 0014000
+#define BSDLY   0020000
+#define   BS0   0000000
+#define   BS1   0020000
+#define VTDLY   0040000
+#define   VT0   0000000
+#define   VT1   0040000
+#define FFDLY   0100000
+#define   FF0   0000000
+#define   FF1   0100000
+
+/* c_cflag bit meaning */
+#define CBAUD   0010017
+#define  B0     0000000         /* hang up */
+#define  B50    0000001
+#define  B75    0000002
+#define  B110   0000003
+#define  B134   0000004
+#define  B150   0000005
+#define  B200   0000006
+#define  B300   0000007
+#define  B600   0000010
+#define  B1200  0000011
+#define  B1800  0000012
+#define  B2400  0000013
+#define  B4800  0000014
+#define  B9600  0000015
+#define  B19200 0000016
+#define  B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE   0000060
+#define   CS5   0000000
+#define   CS6   0000020
+#define   CS7   0000040
+#define   CS8   0000060
+#define CSTOPB  0000100
+#define CREAD   0000200
+#define PARENB  0000400
+#define PARODD  0001000
+#define HUPCL   0002000
+#define CLOCAL  0004000
+#define CBAUDEX 0010000
+#define    BOTHER 0010000               /* non standard rate */
+#define    B57600 0010001
+#define   B115200 0010002
+#define   B230400 0010003
+#define   B460800 0010004
+#define   B500000 0010005
+#define   B576000 0010006
+#define   B921600 0010007
+#define  B1000000 0010010
+#define  B1152000 0010011
+#define  B1500000 0010012
+#define  B2000000 0010013
+#define  B2500000 0010014
+#define  B3000000 0010015
+#define  B3500000 0010016
+#define  B4000000 0010017
+#define CIBAUD    002003600000  /* input baud rate */
+#define CMSPAR    010000000000  /* mark or space (stick) parity */
+#define CRTSCTS   020000000000  /* flow control */
+
+#define IBSHIFT   16            /* Shift from CBAUD to CIBAUD */
+
+/* c_lflag bits */
+#define ISIG    0000001
+#define ICANON  0000002
+#define XCASE   0000004
+#define ECHO    0000010
+#define ECHOE   0000020
+#define ECHOK   0000040
+#define ECHONL  0000100
+#define NOFLSH  0000200
+#define TOSTOP  0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE  0004000
+#define FLUSHO  0010000
+#define PENDIN  0040000
+#define IEXTEN  0100000
+
+/* tcflow() and TCXONC use these */
+#define TCOOFF          0
+#define TCOON           1
+#define TCIOFF          2
+#define TCION           3
+
+/* tcflush() and TCFLSH use these */
+#define TCIFLUSH        0
+#define TCOFLUSH        1
+#define TCIOFLUSH       2
+
+/* tcsetattr uses these */
+#define TCSANOW         0
+#define TCSADRAIN       1
+#define TCSAFLUSH       2
+
+#endif /* _ASM_X86_TERMBITS_H */
diff --git a/include/asm-x86/termbits_32.h b/include/asm-x86/termbits_32.h
deleted file mode 100644
index a21700352e7b..000000000000
--- a/include/asm-x86/termbits_32.h
+++ /dev/null
@@ -1,198 +0,0 @@
-#ifndef __ARCH_I386_TERMBITS_H__
-#define __ARCH_I386_TERMBITS_H__
-
-#include <linux/posix_types.h>
-
-typedef unsigned char   cc_t;
-typedef unsigned int    speed_t;
-typedef unsigned int    tcflag_t;
-
-#define NCCS 19
-struct termios {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-};
-
-struct termios2 {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-        speed_t c_ispeed;               /* input speed */
-        speed_t c_ospeed;               /* output speed */
-};
-
-struct ktermios {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-        speed_t c_ispeed;               /* input speed */
-        speed_t c_ospeed;               /* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK  0000001
-#define BRKINT  0000002
-#define IGNPAR  0000004
-#define PARMRK  0000010
-#define INPCK   0000020
-#define ISTRIP  0000040
-#define INLCR   0000100
-#define IGNCR   0000200
-#define ICRNL   0000400
-#define IUCLC   0001000
-#define IXON    0002000
-#define IXANY   0004000
-#define IXOFF   0010000
-#define IMAXBEL 0020000
-#define IUTF8   0040000
-
-/* c_oflag bits */
-#define OPOST   0000001
-#define OLCUC   0000002
-#define ONLCR   0000004
-#define OCRNL   0000010
-#define ONOCR   0000020
-#define ONLRET  0000040
-#define OFILL   0000100
-#define OFDEL   0000200
-#define NLDLY   0000400
-#define   NL0   0000000
-#define   NL1   0000400
-#define CRDLY   0003000
-#define   CR0   0000000
-#define   CR1   0001000
-#define   CR2   0002000
-#define   CR3   0003000
-#define TABDLY  0014000
-#define   TAB0  0000000
-#define   TAB1  0004000
-#define   TAB2  0010000
-#define   TAB3  0014000
-#define   XTABS 0014000
-#define BSDLY   0020000
-#define   BS0   0000000
-#define   BS1   0020000
-#define VTDLY   0040000
-#define   VT0   0000000
-#define   VT1   0040000
-#define FFDLY   0100000
-#define   FF0   0000000
-#define   FF1   0100000
-
-/* c_cflag bit meaning */
-#define CBAUD   0010017
-#define  B0     0000000         /* hang up */
-#define  B50    0000001
-#define  B75    0000002
-#define  B110   0000003
-#define  B134   0000004
-#define  B150   0000005
-#define  B200   0000006
-#define  B300   0000007
-#define  B600   0000010
-#define  B1200  0000011
-#define  B1800  0000012
-#define  B2400  0000013
-#define  B4800  0000014
-#define  B9600  0000015
-#define  B19200 0000016
-#define  B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE   0000060
-#define   CS5   0000000
-#define   CS6   0000020
-#define   CS7   0000040
-#define   CS8   0000060
-#define CSTOPB  0000100
-#define CREAD   0000200
-#define PARENB  0000400
-#define PARODD  0001000
-#define HUPCL   0002000
-#define CLOCAL  0004000
-#define CBAUDEX 0010000
-#define   BOTHER  0010000
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD    002003600000
-#define CMSPAR    010000000000          /* mark or space (stick) parity */
-#define CRTSCTS   020000000000          /* flow control */
-
-#define IBSHIFT   16            /* Shift from CBAUD to CIBAUD */
-
-/* c_lflag bits */
-#define ISIG    0000001
-#define ICANON  0000002
-#define XCASE   0000004
-#define ECHO    0000010
-#define ECHOE   0000020
-#define ECHOK   0000040
-#define ECHONL  0000100
-#define NOFLSH  0000200
-#define TOSTOP  0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE  0004000
-#define FLUSHO  0010000
-#define PENDIN  0040000
-#define IEXTEN  0100000
-
-/* tcflow() and TCXONC use these */
-#define TCOOFF          0
-#define TCOON           1
-#define TCIOFF          2
-#define TCION           3
-
-/* tcflush() and TCFLSH use these */
-#define TCIFLUSH        0
-#define TCOFLUSH        1
-#define TCIOFLUSH       2
-
-/* tcsetattr uses these */
-#define TCSANOW         0
-#define TCSADRAIN       1
-#define TCSAFLUSH       2
-
-#endif
diff --git a/include/asm-x86/termbits_64.h b/include/asm-x86/termbits_64.h
deleted file mode 100644
index 7405756dd41b..000000000000
--- a/include/asm-x86/termbits_64.h
+++ /dev/null
@@ -1,198 +0,0 @@
-#ifndef __ARCH_X8664_TERMBITS_H__
-#define __ARCH_X8664_TERMBITS_H__
-
-#include <linux/posix_types.h>
-
-typedef unsigned char   cc_t;
-typedef unsigned int    speed_t;
-typedef unsigned int    tcflag_t;
-
-#define NCCS 19
-struct termios {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-};
-
-struct termios2 {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-        speed_t c_ispeed;               /* input speed */
-        speed_t c_ospeed;               /* output speed */
-};
-
-struct ktermios {
-        tcflag_t c_iflag;               /* input mode flags */
-        tcflag_t c_oflag;               /* output mode flags */
-        tcflag_t c_cflag;               /* control mode flags */
-        tcflag_t c_lflag;               /* local mode flags */
-        cc_t c_line;                    /* line discipline */
-        cc_t c_cc[NCCS];                /* control characters */
-        speed_t c_ispeed;               /* input speed */
-        speed_t c_ospeed;               /* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK  0000001
-#define BRKINT  0000002
-#define IGNPAR  0000004
-#define PARMRK  0000010
-#define INPCK   0000020
-#define ISTRIP  0000040
-#define INLCR   0000100
-#define IGNCR   0000200
-#define ICRNL   0000400
-#define IUCLC   0001000
-#define IXON    0002000
-#define IXANY   0004000
-#define IXOFF   0010000
-#define IMAXBEL 0020000
-#define IUTF8   0040000
-
-/* c_oflag bits */
-#define OPOST   0000001
-#define OLCUC   0000002
-#define ONLCR   0000004
-#define OCRNL   0000010
-#define ONOCR   0000020
-#define ONLRET  0000040
-#define OFILL   0000100
-#define OFDEL   0000200
-#define NLDLY   0000400
-#define   NL0   0000000
-#define   NL1   0000400
-#define CRDLY   0003000
-#define   CR0   0000000
-#define   CR1   0001000
-#define   CR2   0002000
-#define   CR3   0003000
-#define TABDLY  0014000
-#define   TAB0  0000000
-#define   TAB1  0004000
-#define   TAB2  0010000
-#define   TAB3  0014000
-#define   XTABS 0014000
-#define BSDLY   0020000
-#define   BS0   0000000
-#define   BS1   0020000
-#define VTDLY   0040000
-#define   VT0   0000000
-#define   VT1   0040000
-#define FFDLY   0100000
-#define   FF0   0000000
-#define   FF1   0100000
-
-/* c_cflag bit meaning */
-#define CBAUD   0010017
-#define  B0     0000000         /* hang up */
-#define  B50    0000001
-#define  B75    0000002
-#define  B110   0000003
-#define  B134   0000004
-#define  B150   0000005
-#define  B200   0000006
-#define  B300   0000007
-#define  B600   0000010
-#define  B1200  0000011
-#define  B1800  0000012
-#define  B2400  0000013
-#define  B4800  0000014
-#define  B9600  0000015
-#define  B19200 0000016
-#define  B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE   0000060
-#define   CS5   0000000
-#define   CS6   0000020
-#define   CS7   0000040
-#define   CS8   0000060
-#define CSTOPB  0000100
-#define CREAD   0000200
-#define PARENB  0000400
-#define PARODD  0001000
-#define HUPCL   0002000
-#define CLOCAL  0004000
-#define CBAUDEX 0010000
-#define    BOTHER 0010000               /* non standard rate */
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD    002003600000  /* input baud rate */
-#define CMSPAR    010000000000          /* mark or space (stick) parity */
-#define CRTSCTS   020000000000          /* flow control */
-
-#define IBSHIFT   16            /* Shift from CBAUD to CIBAUD */
-
-/* c_lflag bits */
-#define ISIG    0000001
-#define ICANON  0000002
-#define XCASE   0000004
-#define ECHO    0000010
-#define ECHOE   0000020
-#define ECHOK   0000040
-#define ECHONL  0000100
-#define NOFLSH  0000200
-#define TOSTOP  0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE  0004000
-#define FLUSHO  0010000
-#define PENDIN  0040000
-#define IEXTEN  0100000
-
-/* tcflow() and TCXONC use these */
-#define TCOOFF          0
-#define TCOON           1
-#define TCIOFF          2
-#define TCION           3
-
-/* tcflush() and TCFLSH use these */
-#define TCIFLUSH        0
-#define TCOFLUSH        1
-#define TCIOFLUSH       2
-
-/* tcsetattr uses these */
-#define TCSANOW         0
-#define TCSADRAIN       1
-#define TCSAFLUSH       2
-
-#endif
diff --git a/include/asm-x86/termios.h b/include/asm-x86/termios.h
index a4f4ae20a591..d501748700d2 100644
--- a/include/asm-x86/termios.h
+++ b/include/asm-x86/termios.h
@@ -1,13 +1,97 @@
+#ifndef _ASM_X86_TERMIOS_H
+#define _ASM_X86_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+        unsigned short ws_row;
+        unsigned short ws_col;
+        unsigned short ws_xpixel;
+        unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+        unsigned short c_iflag;         /* input mode flags */
+        unsigned short c_oflag;         /* output mode flags */
+        unsigned short c_cflag;         /* control mode flags */
+        unsigned short c_lflag;         /* local mode flags */
+        unsigned char c_line;           /* line discipline */
+        unsigned char c_cc[NCC];        /* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE        0x001
+#define TIOCM_DTR       0x002
+#define TIOCM_RTS       0x004
+#define TIOCM_ST        0x008
+#define TIOCM_SR        0x010
+#define TIOCM_CTS       0x020
+#define TIOCM_CAR       0x040
+#define TIOCM_RNG       0x080
+#define TIOCM_DSR       0x100
+#define TIOCM_CD        TIOCM_CAR
+#define TIOCM_RI        TIOCM_RNG
+#define TIOCM_OUT1      0x2000
+#define TIOCM_OUT2      0x4000
+#define TIOCM_LOOP      0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
 #ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "termios_32.h"
-# else
-#  include "termios_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "termios_32.h"
-# else
-#  include "termios_64.h"
-# endif
-#endif
+
+/*      intr=^C         quit=^\         erase=del       kill=^U
+        eof=^D          vtime=\0        vmin=\1         sxtc=\0
+        start=^Q        stop=^S         susp=^Z         eol=\0
+        reprint=^R      discard=^U      werase=^W       lnext=^V
+        eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+        unsigned short __tmp; \
+        get_user(__tmp,&(termio)->x); \
+        *(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+        SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+        copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+        put_user((termios)->c_iflag, &(termio)->c_iflag); \
+        put_user((termios)->c_oflag, &(termio)->c_oflag); \
+        put_user((termios)->c_cflag, &(termio)->c_cflag); \
+        put_user((termios)->c_lflag, &(termio)->c_lflag); \
+        put_user((termios)->c_line,  &(termio)->c_line); \
+        copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) \
+        copy_from_user(k, u, sizeof(struct termios2))
+
+#define kernel_termios_to_user_termios(u, k) \
+        copy_to_user(u, k, sizeof(struct termios2))
+
+#define user_termios_to_kernel_termios_1(k, u) \
+        copy_from_user(k, u, sizeof(struct termios))
+
+#define kernel_termios_to_user_termios_1(u, k) \
+        copy_to_user(u, k, sizeof(struct termios))
+
+#endif  /* __KERNEL__ */
+
+#endif /* _ASM_X86_TERMIOS_H */
diff --git a/include/asm-x86/termios_32.h b/include/asm-x86/termios_32.h
deleted file mode 100644
index 6fdb2c841b73..000000000000
--- a/include/asm-x86/termios_32.h
+++ /dev/null
@@ -1,90 +0,0 @@
-#ifndef _I386_TERMIOS_H
-#define _I386_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
-        unsigned short ws_row;
-        unsigned short ws_col;
-        unsigned short ws_xpixel;
-        unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-        unsigned short c_iflag;         /* input mode flags */
-        unsigned short c_oflag;         /* output mode flags */
-        unsigned short c_cflag;         /* control mode flags */
-        unsigned short c_lflag;         /* local mode flags */
-        unsigned char c_line;           /* line discipline */
-        unsigned char c_cc[NCC];        /* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE        0x001
-#define TIOCM_DTR       0x002
-#define TIOCM_RTS       0x004
-#define TIOCM_ST        0x008
-#define TIOCM_SR        0x010
-#define TIOCM_CTS       0x020
-#define TIOCM_CAR       0x040
-#define TIOCM_RNG       0x080
-#define TIOCM_DSR       0x100
-#define TIOCM_CD        TIOCM_CAR
-#define TIOCM_RI        TIOCM_RNG
-#define TIOCM_OUT1      0x2000
-#define TIOCM_OUT2      0x4000
-#define TIOCM_LOOP      0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#ifdef __KERNEL__
-
-/*      intr=^C         quit=^\         erase=del       kill=^U
-        eof=^D          vtime=\0        vmin=\1         sxtc=\0
-        start=^Q        stop=^S         susp=^Z         eol=\0
-        reprint=^R      discard=^U      werase=^W       lnext=^V
-        eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
-        unsigned short __tmp; \
-        get_user(__tmp,&(termio)->x); \
-        *(unsigned short *) &(termios)->x = __tmp; \
-}
-
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
-        copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
-        put_user((termios)->c_iflag, &(termio)->c_iflag); \
-        put_user((termios)->c_oflag, &(termio)->c_oflag); \
-        put_user((termios)->c_cflag, &(termio)->c_cflag); \
-        put_user((termios)->c_lflag, &(termio)->c_lflag); \
-        put_user((termios)->c_line,  &(termio)->c_line); \
-        copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
-#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
-
-#endif  /* __KERNEL__ */
-
-#endif  /* _I386_TERMIOS_H */
diff --git a/include/asm-x86/termios_64.h b/include/asm-x86/termios_64.h
deleted file mode 100644
index 35ee59b78329..000000000000
--- a/include/asm-x86/termios_64.h
+++ /dev/null
@@ -1,90 +0,0 @@
-#ifndef _X8664_TERMIOS_H
-#define _X8664_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
-        unsigned short ws_row;
-        unsigned short ws_col;
-        unsigned short ws_xpixel;
-        unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-        unsigned short c_iflag;         /* input mode flags */
-        unsigned short c_oflag;         /* output mode flags */
-        unsigned short c_cflag;         /* control mode flags */
-        unsigned short c_lflag;         /* local mode flags */
-        unsigned char c_line;           /* line discipline */
-        unsigned char c_cc[NCC];        /* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE        0x001
-#define TIOCM_DTR       0x002
-#define TIOCM_RTS       0x004
-#define TIOCM_ST        0x008
-#define TIOCM_SR        0x010
-#define TIOCM_CTS       0x020
-#define TIOCM_CAR       0x040
-#define TIOCM_RNG       0x080
-#define TIOCM_DSR       0x100
-#define TIOCM_CD        TIOCM_CAR
-#define TIOCM_RI        TIOCM_RNG
-#define TIOCM_OUT1      0x2000
-#define TIOCM_OUT2      0x4000
-#define TIOCM_LOOP      0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#ifdef __KERNEL__
-
-/*      intr=^C         quit=^\         erase=del       kill=^U
-        eof=^D          vtime=\0        vmin=\1         sxtc=\0
-        start=^Q        stop=^S         susp=^Z         eol=\0
-        reprint=^R      discard=^U      werase=^W       lnext=^V
-        eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
-        unsigned short __tmp; \
-        get_user(__tmp,&(termio)->x); \
-        *(unsigned short *) &(termios)->x = __tmp; \
-}
-
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
-        SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
-        copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
-        put_user((termios)->c_iflag, &(termio)->c_iflag); \
-        put_user((termios)->c_oflag, &(termio)->c_oflag); \
-        put_user((termios)->c_cflag, &(termio)->c_cflag); \
-        put_user((termios)->c_lflag, &(termio)->c_lflag); \
-        put_user((termios)->c_line,  &(termio)->c_line); \
-        copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
-#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
-
-#endif  /* __KERNEL__ */
-
-#endif  /* _X8664_TERMIOS_H */
diff --git a/include/asm-x86/tlb.h b/include/asm-x86/tlb.h
index 7d55c3762b43..e4e9e2d07a93 100644
--- a/include/asm-x86/tlb.h
+++ b/include/asm-x86/tlb.h
@@ -1,5 +1,11 @@
-#ifdef CONFIG_X86_32
-# include "tlb_32.h"
-#else
-# include "tlb_64.h"
+#ifndef _ASM_X86_TLB_H
+#define _ASM_X86_TLB_H
+
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#include <asm-generic/tlb.h>
+
 #endif
diff --git a/include/asm-x86/tlb_32.h b/include/asm-x86/tlb_32.h
deleted file mode 100644
index c006c5c92bea..000000000000
--- a/include/asm-x86/tlb_32.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef _I386_TLB_H
-#define _I386_TLB_H
-
-/*
- * x86 doesn't need any special per-pte or
- * per-vma handling..
- */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it
- * fills up.
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#include <asm-generic/tlb.h>
-
-#endif
diff --git a/include/asm-x86/tlb_64.h b/include/asm-x86/tlb_64.h
deleted file mode 100644
index cd4c3c590a0e..000000000000
--- a/include/asm-x86/tlb_64.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef TLB_H
-#define TLB_H 1
-
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#include <asm-generic/tlb.h>
-
-#endif
diff --git a/include/asm-x86/types.h b/include/asm-x86/types.h
index a777a9b83974..63733f315688 100644
--- a/include/asm-x86/types.h
+++ b/include/asm-x86/types.h
@@ -1,13 +1,70 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "types_32.h"
-# else
-#  include "types_64.h"
+#ifndef _ASM_X86_TYPES_H
+#define _ASM_X86_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned short umode_t;
+
+/*
+ * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
+ * header files exported to user space
+ */
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+#ifdef __i386__
+# ifdef __GNUC__
+__extension__ typedef __signed__ long long __s64;
+__extension__ typedef unsigned long long __u64;
 # endif
 #else
-# ifdef __i386__
-#  include "types_32.h"
-# else
-#  include "types_64.h"
-# endif
+typedef __signed__ long long __s64;
+typedef unsigned long long __u64;
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#ifdef CONFIG_X86_32
+# define BITS_PER_LONG 32
+#else
+# define BITS_PER_LONG 64
+#endif
+
+#ifndef __ASSEMBLY__
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+typedef u64 dma64_addr_t;
+#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G)
+/* DMA addresses come in 32-bit and 64-bit flavours. */
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/include/asm-x86/types_32.h b/include/asm-x86/types_32.h
deleted file mode 100644
index faca1922c4c3..000000000000
--- a/include/asm-x86/types_32.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef _I386_TYPES_H
-#define _I386_TYPES_H
-
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-/*
- * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
- * header files exported to user space
- */
-
-typedef __signed__ char __s8;
-typedef unsigned char __u8;
-
-typedef __signed__ short __s16;
-typedef unsigned short __u16;
-
-typedef __signed__ int __s32;
-typedef unsigned int __u32;
-
-#if defined(__GNUC__)
-__extension__ typedef __signed__ long long __s64;
-__extension__ typedef unsigned long long __u64;
-#endif
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-#ifdef __KERNEL__
-
-#define BITS_PER_LONG 32
-
-#ifndef __ASSEMBLY__
-
-
-typedef signed char s8;
-typedef unsigned char u8;
-
-typedef signed short s16;
-typedef unsigned short u16;
-
-typedef signed int s32;
-typedef unsigned int u32;
-
-typedef signed long long s64;
-typedef unsigned long long u64;
-
-/* DMA addresses come in generic and 64-bit flavours.  */
-
-#ifdef CONFIG_HIGHMEM64G
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-typedef u64 dma64_addr_t;
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/include/asm-x86/types_64.h b/include/asm-x86/types_64.h
deleted file mode 100644
index 2d4491aae281..000000000000
--- a/include/asm-x86/types_64.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _X86_64_TYPES_H
-#define _X86_64_TYPES_H
-
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-/*
- * __xx is ok: it doesn't pollute the POSIX namespace. Use these in the
- * header files exported to user space
- */
-
-typedef __signed__ char __s8;
-typedef unsigned char __u8;
-
-typedef __signed__ short __s16;
-typedef unsigned short __u16;
-
-typedef __signed__ int __s32;
-typedef unsigned int __u32;
-
-typedef __signed__ long long __s64;
-typedef unsigned long long  __u64;
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-#ifdef __KERNEL__
-
-#define BITS_PER_LONG 64
-
-#ifndef __ASSEMBLY__
-
-typedef signed char s8;
-typedef unsigned char u8;
-
-typedef signed short s16;
-typedef unsigned short u16;
-
-typedef signed int s32;
-typedef unsigned int u32;
-
-typedef signed long long s64;
-typedef unsigned long long u64;
-
-typedef u64 dma64_addr_t;
-typedef u64 dma_addr_t;
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
index 175c8cb59731..50a79f7fcde9 100644
--- a/include/asm-x86/ucontext.h
+++ b/include/asm-x86/ucontext.h
@@ -1,13 +1,12 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "ucontext_32.h"
-# else
-#  include "ucontext_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "ucontext_32.h"
-# else
-#  include "ucontext_64.h"
-# endif
-#endif
+#ifndef _ASM_X86_UCONTEXT_H
+#define _ASM_X86_UCONTEXT_H
+
+struct ucontext {
+        unsigned long     uc_flags;
+        struct ucontext  *uc_link;
+        stack_t           uc_stack;
+        struct sigcontext uc_mcontext;
+        sigset_t          uc_sigmask;   /* mask last for extensibility */
+};
+
+#endif /* _ASM_X86_UCONTEXT_H */
diff --git a/include/asm-x86/ucontext_32.h b/include/asm-x86/ucontext_32.h
deleted file mode 100644
index b0db36925f55..000000000000
--- a/include/asm-x86/ucontext_32.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASMi386_UCONTEXT_H
-#define _ASMi386_UCONTEXT_H
-
-struct ucontext {
-        unsigned long     uc_flags;
-        struct ucontext  *uc_link;
-        stack_t           uc_stack;
-        struct sigcontext uc_mcontext;
-        sigset_t          uc_sigmask;   /* mask last for extensibility */
-};
-
-#endif /* !_ASMi386_UCONTEXT_H */
diff --git a/include/asm-x86/ucontext_64.h b/include/asm-x86/ucontext_64.h
deleted file mode 100644
index 159a3da9e112..000000000000
--- a/include/asm-x86/ucontext_64.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASMX8664_UCONTEXT_H
-#define _ASMX8664_UCONTEXT_H
-
-struct ucontext {
-        unsigned long     uc_flags;
-        struct ucontext  *uc_link;
-        stack_t           uc_stack;
-        struct sigcontext uc_mcontext;
-        sigset_t          uc_sigmask;   /* mask last for extensibility */
-};
-
-#endif
diff --git a/include/asm-x86/unaligned.h b/include/asm-x86/unaligned.h
index 68067150fbcb..913598d4f761 100644
--- a/include/asm-x86/unaligned.h
+++ b/include/asm-x86/unaligned.h
@@ -1,5 +1,37 @@
-#ifdef CONFIG_X86_32
-# include "unaligned_32.h"
-#else
-# include "unaligned_64.h"
-#endif
+#ifndef _ASM_X86_UNALIGNED_H
+#define _ASM_X86_UNALIGNED_H
+
+/*
+ * The x86 can do unaligned accesses itself.
+ *
+ * The strange macros are there to make sure these can't
+ * be misused in a way that makes them not work on other
+ * architectures where unaligned accesses aren't as simple.
+ */
+
+/**
+ * get_unaligned - get value from possibly mis-aligned location
+ * @ptr: pointer to value
+ *
+ * This macro should be used for accessing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. retrieving a u16 value from a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define get_unaligned(ptr) (*(ptr))
+
+/**
+ * put_unaligned - put value to a possibly mis-aligned location
+ * @val: value to place
+ * @ptr: pointer to location
+ *
+ * This macro should be used for placing values larger in size than
+ * single bytes at locations that are expected to be improperly aligned,
+ * e.g. writing a u16 value to a location not u16-aligned.
+ *
+ * Note that unaligned accesses can be very expensive on some architectures.
+ */
+#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+
+#endif /* _ASM_X86_UNALIGNED_H */
diff --git a/include/asm-x86/unaligned_32.h b/include/asm-x86/unaligned_32.h
deleted file mode 100644
index 7acd7957621e..000000000000
--- a/include/asm-x86/unaligned_32.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef __I386_UNALIGNED_H
-#define __I386_UNALIGNED_H
-
-/*
- * The i386 can do unaligned accesses itself. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
- */
-
-/**
- * get_unaligned - get value from possibly mis-aligned location
- * @ptr: pointer to value
- *
- * This macro should be used for accessing values larger in size than 
- * single bytes at locations that are expected to be improperly aligned, 
- * e.g. retrieving a u16 value from a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define get_unaligned(ptr) (*(ptr))
-
-/**
- * put_unaligned - put value to a possibly mis-aligned location
- * @val: value to place
- * @ptr: pointer to location
- *
- * This macro should be used for placing values larger in size than 
- * single bytes at locations that are expected to be improperly aligned, 
- * e.g. writing a u16 value to a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif
diff --git a/include/asm-x86/unaligned_64.h b/include/asm-x86/unaligned_64.h
deleted file mode 100644
index d4bf78dc6f39..000000000000
--- a/include/asm-x86/unaligned_64.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef __X8664_UNALIGNED_H
-#define __X8664_UNALIGNED_H
-
-/*
- * The x86-64 can do unaligned accesses itself. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
- */
-
-/**
- * get_unaligned - get value from possibly mis-aligned location
- * @ptr: pointer to value
- *
- * This macro should be used for accessing values larger in size than 
- * single bytes at locations that are expected to be improperly aligned, 
- * e.g. retrieving a u16 value from a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define get_unaligned(ptr) (*(ptr))
-
-/**
- * put_unaligned - put value to a possibly mis-aligned location
- * @val: value to place
- * @ptr: pointer to location
- *
- * This macro should be used for placing values larger in size than 
- * single bytes at locations that are expected to be improperly aligned, 
- * e.g. writing a u16 value to a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
index fc4e73f5f1fa..5ff4d3e24c34 100644
--- a/include/asm-x86/unistd_64.h
+++ b/include/asm-x86/unistd_64.h
@@ -2,635 +2,638 @@
 #define _ASM_X86_64_UNISTD_H_
 
 #ifndef __SYSCALL
-#define __SYSCALL(a,b) 
+#define __SYSCALL(a,b)
 #endif
 
 /*
  * This file contains the system call numbers.
- * 
+ *
  * Note: holes are not allowed.
  */
 
 /* at least 8 syscall per cacheline */
-#define __NR_read                                0
+#define __NR_read                               0
 __SYSCALL(__NR_read, sys_read)
-#define __NR_write                               1
+#define __NR_write                              1
 __SYSCALL(__NR_write, sys_write)
-#define __NR_open                                2
+#define __NR_open                               2
 __SYSCALL(__NR_open, sys_open)
-#define __NR_close                               3
+#define __NR_close                              3
 __SYSCALL(__NR_close, sys_close)
-#define __NR_stat                                4
+#define __NR_stat                               4
 __SYSCALL(__NR_stat, sys_newstat)
-#define __NR_fstat                               5
+#define __NR_fstat                              5
 __SYSCALL(__NR_fstat, sys_newfstat)
-#define __NR_lstat                               6
+#define __NR_lstat                              6
 __SYSCALL(__NR_lstat, sys_newlstat)
-#define __NR_poll                                7
+#define __NR_poll                               7
 __SYSCALL(__NR_poll, sys_poll)
 
-#define __NR_lseek                               8
+#define __NR_lseek                              8
 __SYSCALL(__NR_lseek, sys_lseek)
-#define __NR_mmap                                9
+#define __NR_mmap                               9
 __SYSCALL(__NR_mmap, sys_mmap)
-#define __NR_mprotect                           10
+#define __NR_mprotect                           10
 __SYSCALL(__NR_mprotect, sys_mprotect)
-#define __NR_munmap                             11
+#define __NR_munmap                             11
 __SYSCALL(__NR_munmap, sys_munmap)
-#define __NR_brk                                12
+#define __NR_brk                                12
 __SYSCALL(__NR_brk, sys_brk)
-#define __NR_rt_sigaction                       13
+#define __NR_rt_sigaction                       13
 __SYSCALL(__NR_rt_sigaction, sys_rt_sigaction)
-#define __NR_rt_sigprocmask                     14
+#define __NR_rt_sigprocmask                     14
 __SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
-#define __NR_rt_sigreturn                       15
+#define __NR_rt_sigreturn                       15
 __SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn)
 
-#define __NR_ioctl                              16
+#define __NR_ioctl                              16
 __SYSCALL(__NR_ioctl, sys_ioctl)
-#define __NR_pread64                            17
+#define __NR_pread64                            17
 __SYSCALL(__NR_pread64, sys_pread64)
-#define __NR_pwrite64                           18
+#define __NR_pwrite64                           18
 __SYSCALL(__NR_pwrite64, sys_pwrite64)
-#define __NR_readv                              19
+#define __NR_readv                              19
 __SYSCALL(__NR_readv, sys_readv)
-#define __NR_writev                             20
+#define __NR_writev                             20
 __SYSCALL(__NR_writev, sys_writev)
-#define __NR_access                             21
+#define __NR_access                             21
 __SYSCALL(__NR_access, sys_access)
-#define __NR_pipe                               22
+#define __NR_pipe                               22
 __SYSCALL(__NR_pipe, sys_pipe)
-#define __NR_select                             23
+#define __NR_select                             23
 __SYSCALL(__NR_select, sys_select)
 
-#define __NR_sched_yield                        24
+#define __NR_sched_yield                        24
 __SYSCALL(__NR_sched_yield, sys_sched_yield)
-#define __NR_mremap                             25
+#define __NR_mremap                             25
 __SYSCALL(__NR_mremap, sys_mremap)
-#define __NR_msync                              26
+#define __NR_msync                              26
 __SYSCALL(__NR_msync, sys_msync)
-#define __NR_mincore                            27
+#define __NR_mincore                            27
 __SYSCALL(__NR_mincore, sys_mincore)
-#define __NR_madvise                            28
+#define __NR_madvise                            28
 __SYSCALL(__NR_madvise, sys_madvise)
-#define __NR_shmget                             29
+#define __NR_shmget                             29
 __SYSCALL(__NR_shmget, sys_shmget)
-#define __NR_shmat                              30
+#define __NR_shmat                              30
 __SYSCALL(__NR_shmat, sys_shmat)
-#define __NR_shmctl                             31
+#define __NR_shmctl                             31
 __SYSCALL(__NR_shmctl, sys_shmctl)
 
-#define __NR_dup                                32
+#define __NR_dup                                32
 __SYSCALL(__NR_dup, sys_dup)
-#define __NR_dup2                               33
+#define __NR_dup2                               33
 __SYSCALL(__NR_dup2, sys_dup2)
-#define __NR_pause                              34
+#define __NR_pause                              34
 __SYSCALL(__NR_pause, sys_pause)
-#define __NR_nanosleep                          35
+#define __NR_nanosleep                          35
 __SYSCALL(__NR_nanosleep, sys_nanosleep)
-#define __NR_getitimer                          36
+#define __NR_getitimer                          36
 __SYSCALL(__NR_getitimer, sys_getitimer)
-#define __NR_alarm                              37
+#define __NR_alarm                              37
 __SYSCALL(__NR_alarm, sys_alarm)
-#define __NR_setitimer                          38
+#define __NR_setitimer                          38
 __SYSCALL(__NR_setitimer, sys_setitimer)
-#define __NR_getpid                             39
+#define __NR_getpid                             39
 __SYSCALL(__NR_getpid, sys_getpid)
 
-#define __NR_sendfile                           40
+#define __NR_sendfile                           40
 __SYSCALL(__NR_sendfile, sys_sendfile64)
-#define __NR_socket                             41
+#define __NR_socket                             41
 __SYSCALL(__NR_socket, sys_socket)
-#define __NR_connect                            42
+#define __NR_connect                            42
 __SYSCALL(__NR_connect, sys_connect)
-#define __NR_accept                             43
+#define __NR_accept                             43
 __SYSCALL(__NR_accept, sys_accept)
-#define __NR_sendto                             44
+#define __NR_sendto                             44
 __SYSCALL(__NR_sendto, sys_sendto)
-#define __NR_recvfrom                           45
+#define __NR_recvfrom                           45
 __SYSCALL(__NR_recvfrom, sys_recvfrom)
-#define __NR_sendmsg                            46
+#define __NR_sendmsg                            46
 __SYSCALL(__NR_sendmsg, sys_sendmsg)
-#define __NR_recvmsg                            47
+#define __NR_recvmsg                            47
 __SYSCALL(__NR_recvmsg, sys_recvmsg)
 
-#define __NR_shutdown                           48
+#define __NR_shutdown                           48
 __SYSCALL(__NR_shutdown, sys_shutdown)
-#define __NR_bind                               49
+#define __NR_bind                               49
 __SYSCALL(__NR_bind, sys_bind)
-#define __NR_listen                             50
+#define __NR_listen                             50
 __SYSCALL(__NR_listen, sys_listen)
-#define __NR_getsockname                        51
+#define __NR_getsockname                        51
 __SYSCALL(__NR_getsockname, sys_getsockname)
-#define __NR_getpeername                        52
+#define __NR_getpeername                        52
 __SYSCALL(__NR_getpeername, sys_getpeername)
-#define __NR_socketpair                         53
+#define __NR_socketpair                         53
 __SYSCALL(__NR_socketpair, sys_socketpair)
-#define __NR_setsockopt                         54
+#define __NR_setsockopt                         54
 __SYSCALL(__NR_setsockopt, sys_setsockopt)
-#define __NR_getsockopt                         55
+#define __NR_getsockopt                         55
 __SYSCALL(__NR_getsockopt, sys_getsockopt)
 
-#define __NR_clone                              56
+#define __NR_clone                              56
 __SYSCALL(__NR_clone, stub_clone)
-#define __NR_fork                               57
-__SYSCALL(__NR_fork, stub_fork) 
-#define __NR_vfork                              58
+#define __NR_fork                               57
+__SYSCALL(__NR_fork, stub_fork)
+#define __NR_vfork                              58
 __SYSCALL(__NR_vfork, stub_vfork)
-#define __NR_execve                             59
+#define __NR_execve                             59
 __SYSCALL(__NR_execve, stub_execve)
-#define __NR_exit                               60
+#define __NR_exit                               60
 __SYSCALL(__NR_exit, sys_exit)
-#define __NR_wait4                              61
+#define __NR_wait4                              61
 __SYSCALL(__NR_wait4, sys_wait4)
-#define __NR_kill                               62
+#define __NR_kill                               62
 __SYSCALL(__NR_kill, sys_kill)
-#define __NR_uname                              63
+#define __NR_uname                              63
 __SYSCALL(__NR_uname, sys_uname)
 
-#define __NR_semget                             64
+#define __NR_semget                             64
 __SYSCALL(__NR_semget, sys_semget)
-#define __NR_semop                              65
+#define __NR_semop                              65
 __SYSCALL(__NR_semop, sys_semop)
-#define __NR_semctl                             66
+#define __NR_semctl                             66
 __SYSCALL(__NR_semctl, sys_semctl)
-#define __NR_shmdt                              67
+#define __NR_shmdt                              67
 __SYSCALL(__NR_shmdt, sys_shmdt)
-#define __NR_msgget                             68
+#define __NR_msgget                             68
 __SYSCALL(__NR_msgget, sys_msgget)
-#define __NR_msgsnd                             69
+#define __NR_msgsnd                             69
 __SYSCALL(__NR_msgsnd, sys_msgsnd)
-#define __NR_msgrcv                             70
+#define __NR_msgrcv                             70
 __SYSCALL(__NR_msgrcv, sys_msgrcv)
-#define __NR_msgctl                             71
+#define __NR_msgctl                             71
 __SYSCALL(__NR_msgctl, sys_msgctl)
 
-#define __NR_fcntl                              72
+#define __NR_fcntl                              72
 __SYSCALL(__NR_fcntl, sys_fcntl)
-#define __NR_flock                              73
+#define __NR_flock                              73
 __SYSCALL(__NR_flock, sys_flock)
-#define __NR_fsync                              74
+#define __NR_fsync                              74
 __SYSCALL(__NR_fsync, sys_fsync)
-#define __NR_fdatasync                          75
+#define __NR_fdatasync                          75
 __SYSCALL(__NR_fdatasync, sys_fdatasync)
-#define __NR_truncate                           76
+#define __NR_truncate                           76
 __SYSCALL(__NR_truncate, sys_truncate)
-#define __NR_ftruncate                          77
+#define __NR_ftruncate                          77
 __SYSCALL(__NR_ftruncate, sys_ftruncate)
-#define __NR_getdents                           78
+#define __NR_getdents                           78
 __SYSCALL(__NR_getdents, sys_getdents)
-#define __NR_getcwd                             79
+#define __NR_getcwd                             79
 __SYSCALL(__NR_getcwd, sys_getcwd)
 
-#define __NR_chdir                              80
+#define __NR_chdir                              80
 __SYSCALL(__NR_chdir, sys_chdir)
-#define __NR_fchdir                             81
+#define __NR_fchdir                             81
 __SYSCALL(__NR_fchdir, sys_fchdir)
-#define __NR_rename                             82
+#define __NR_rename                             82
 __SYSCALL(__NR_rename, sys_rename)
-#define __NR_mkdir                              83
+#define __NR_mkdir                              83
 __SYSCALL(__NR_mkdir, sys_mkdir)
-#define __NR_rmdir                              84
+#define __NR_rmdir                              84
 __SYSCALL(__NR_rmdir, sys_rmdir)
-#define __NR_creat                              85
+#define __NR_creat                              85
 __SYSCALL(__NR_creat, sys_creat)
-#define __NR_link                               86
+#define __NR_link                               86
 __SYSCALL(__NR_link, sys_link)
-#define __NR_unlink                             87
+#define __NR_unlink                             87
 __SYSCALL(__NR_unlink, sys_unlink)
 
-#define __NR_symlink                            88
+#define __NR_symlink                            88
 __SYSCALL(__NR_symlink, sys_symlink)
-#define __NR_readlink                           89
+#define __NR_readlink                           89
 __SYSCALL(__NR_readlink, sys_readlink)
-#define __NR_chmod                              90
+#define __NR_chmod                              90
 __SYSCALL(__NR_chmod, sys_chmod)
-#define __NR_fchmod                             91
+#define __NR_fchmod                             91
 __SYSCALL(__NR_fchmod, sys_fchmod)
-#define __NR_chown                              92
+#define __NR_chown                              92
 __SYSCALL(__NR_chown, sys_chown)
-#define __NR_fchown                             93
+#define __NR_fchown                             93
 __SYSCALL(__NR_fchown, sys_fchown)
-#define __NR_lchown                             94
+#define __NR_lchown                             94
 __SYSCALL(__NR_lchown, sys_lchown)
-#define __NR_umask                              95
+#define __NR_umask                              95
 __SYSCALL(__NR_umask, sys_umask)
 
-#define __NR_gettimeofday                       96
+#define __NR_gettimeofday                       96
 __SYSCALL(__NR_gettimeofday, sys_gettimeofday)
-#define __NR_getrlimit                          97
+#define __NR_getrlimit                          97
 __SYSCALL(__NR_getrlimit, sys_getrlimit)
-#define __NR_getrusage                          98
+#define __NR_getrusage                          98
 __SYSCALL(__NR_getrusage, sys_getrusage)
-#define __NR_sysinfo                            99
+#define __NR_sysinfo                            99
 __SYSCALL(__NR_sysinfo, sys_sysinfo)
-#define __NR_times                             100
+#define __NR_times                              100
 __SYSCALL(__NR_times, sys_times)
-#define __NR_ptrace                            101
+#define __NR_ptrace                             101
 __SYSCALL(__NR_ptrace, sys_ptrace)
-#define __NR_getuid                            102
+#define __NR_getuid                             102
 __SYSCALL(__NR_getuid, sys_getuid)
-#define __NR_syslog                            103
+#define __NR_syslog                             103
 __SYSCALL(__NR_syslog, sys_syslog)
 
 /* at the very end the stuff that never runs during the benchmarks */
-#define __NR_getgid                            104
+#define __NR_getgid                             104
 __SYSCALL(__NR_getgid, sys_getgid)
-#define __NR_setuid                            105
+#define __NR_setuid                             105
 __SYSCALL(__NR_setuid, sys_setuid)
-#define __NR_setgid                            106
+#define __NR_setgid                             106
 __SYSCALL(__NR_setgid, sys_setgid)
-#define __NR_geteuid                           107
+#define __NR_geteuid                            107
 __SYSCALL(__NR_geteuid, sys_geteuid)
-#define __NR_getegid                           108
+#define __NR_getegid                            108
 __SYSCALL(__NR_getegid, sys_getegid)
-#define __NR_setpgid                           109
+#define __NR_setpgid                            109
 __SYSCALL(__NR_setpgid, sys_setpgid)
-#define __NR_getppid                           110
+#define __NR_getppid                            110
 __SYSCALL(__NR_getppid, sys_getppid)
-#define __NR_getpgrp                           111
+#define __NR_getpgrp                            111
 __SYSCALL(__NR_getpgrp, sys_getpgrp)
 
-#define __NR_setsid                            112
+#define __NR_setsid                             112
 __SYSCALL(__NR_setsid, sys_setsid)
-#define __NR_setreuid                          113
+#define __NR_setreuid                           113
 __SYSCALL(__NR_setreuid, sys_setreuid)
-#define __NR_setregid                          114
+#define __NR_setregid                           114
 __SYSCALL(__NR_setregid, sys_setregid)
-#define __NR_getgroups                         115
+#define __NR_getgroups                          115
 __SYSCALL(__NR_getgroups, sys_getgroups)
-#define __NR_setgroups                         116
+#define __NR_setgroups                          116
 __SYSCALL(__NR_setgroups, sys_setgroups)
-#define __NR_setresuid                         117
+#define __NR_setresuid                          117
 __SYSCALL(__NR_setresuid, sys_setresuid)
-#define __NR_getresuid                         118
+#define __NR_getresuid                          118
 __SYSCALL(__NR_getresuid, sys_getresuid)
-#define __NR_setresgid                         119
+#define __NR_setresgid                          119
 __SYSCALL(__NR_setresgid, sys_setresgid)
 
-#define __NR_getresgid                         120
+#define __NR_getresgid                          120
 __SYSCALL(__NR_getresgid, sys_getresgid)
-#define __NR_getpgid                           121
+#define __NR_getpgid                            121
 __SYSCALL(__NR_getpgid, sys_getpgid)
-#define __NR_setfsuid                          122
+#define __NR_setfsuid                           122
 __SYSCALL(__NR_setfsuid, sys_setfsuid)
-#define __NR_setfsgid                          123
+#define __NR_setfsgid                           123
 __SYSCALL(__NR_setfsgid, sys_setfsgid)
-#define __NR_getsid                            124
+#define __NR_getsid                             124
 __SYSCALL(__NR_getsid, sys_getsid)
-#define __NR_capget                            125
+#define __NR_capget                             125
 __SYSCALL(__NR_capget, sys_capget)
-#define __NR_capset                            126
+#define __NR_capset                             126
 __SYSCALL(__NR_capset, sys_capset)
 
-#define __NR_rt_sigpending                     127
+#define __NR_rt_sigpending                      127
 __SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
-#define __NR_rt_sigtimedwait                   128
+#define __NR_rt_sigtimedwait                    128
 __SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
-#define __NR_rt_sigqueueinfo                   129
+#define __NR_rt_sigqueueinfo                    129
 __SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
-#define __NR_rt_sigsuspend                     130
+#define __NR_rt_sigsuspend                      130
 __SYSCALL(__NR_rt_sigsuspend, stub_rt_sigsuspend)
-#define __NR_sigaltstack                       131
+#define __NR_sigaltstack                        131
 __SYSCALL(__NR_sigaltstack, stub_sigaltstack)
-#define __NR_utime                             132
+#define __NR_utime                              132
 __SYSCALL(__NR_utime, sys_utime)
-#define __NR_mknod                             133
+#define __NR_mknod                              133
 __SYSCALL(__NR_mknod, sys_mknod)
 
 /* Only needed for a.out */
-#define __NR_uselib                            134
+#define __NR_uselib                             134
 __SYSCALL(__NR_uselib, sys_ni_syscall)
-#define __NR_personality                       135
+#define __NR_personality                        135
 __SYSCALL(__NR_personality, sys_personality)
 
-#define __NR_ustat                             136
+#define __NR_ustat                              136
 __SYSCALL(__NR_ustat, sys_ustat)
-#define __NR_statfs                            137
+#define __NR_statfs                             137
 __SYSCALL(__NR_statfs, sys_statfs)
-#define __NR_fstatfs                           138
+#define __NR_fstatfs                            138
 __SYSCALL(__NR_fstatfs, sys_fstatfs)
-#define __NR_sysfs                             139
+#define __NR_sysfs                              139
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
-#define __NR_getpriority                       140
+#define __NR_getpriority                        140
 __SYSCALL(__NR_getpriority, sys_getpriority)
-#define __NR_setpriority                       141
+#define __NR_setpriority                        141
 __SYSCALL(__NR_setpriority, sys_setpriority)
-#define __NR_sched_setparam                    142
+#define __NR_sched_setparam                     142
 __SYSCALL(__NR_sched_setparam, sys_sched_setparam)
-#define __NR_sched_getparam                    143
+#define __NR_sched_getparam                     143
 __SYSCALL(__NR_sched_getparam, sys_sched_getparam)
-#define __NR_sched_setscheduler                144
+#define __NR_sched_setscheduler                 144
 __SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
-#define __NR_sched_getscheduler                145
+#define __NR_sched_getscheduler                 145
 __SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
-#define __NR_sched_get_priority_max            146
+#define __NR_sched_get_priority_max             146
 __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
-#define __NR_sched_get_priority_min            147
+#define __NR_sched_get_priority_min             147
 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
-#define __NR_sched_rr_get_interval             148
+#define __NR_sched_rr_get_interval              148
 __SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
 
-#define __NR_mlock                             149
+#define __NR_mlock                              149
 __SYSCALL(__NR_mlock, sys_mlock)
-#define __NR_munlock                           150
+#define __NR_munlock                            150
 __SYSCALL(__NR_munlock, sys_munlock)
-#define __NR_mlockall                          151
+#define __NR_mlockall                           151
 __SYSCALL(__NR_mlockall, sys_mlockall)
-#define __NR_munlockall                        152
+#define __NR_munlockall                         152
 __SYSCALL(__NR_munlockall, sys_munlockall)
 
-#define __NR_vhangup                           153
+#define __NR_vhangup                            153
 __SYSCALL(__NR_vhangup, sys_vhangup)
 
-#define __NR_modify_ldt                        154
+#define __NR_modify_ldt                         154
 __SYSCALL(__NR_modify_ldt, sys_modify_ldt)
 
-#define __NR_pivot_root                        155
+#define __NR_pivot_root                         155
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
-#define __NR__sysctl                           156
+#define __NR__sysctl                            156
 __SYSCALL(__NR__sysctl, sys_sysctl)
 
-#define __NR_prctl                             157
+#define __NR_prctl                              157
 __SYSCALL(__NR_prctl, sys_prctl)
-#define __NR_arch_prctl                        158
-__SYSCALL(__NR_arch_prctl,      sys_arch_prctl) 
+#define __NR_arch_prctl                         158
+__SYSCALL(__NR_arch_prctl, sys_arch_prctl)
 
-#define __NR_adjtimex                          159
+#define __NR_adjtimex                           159
 __SYSCALL(__NR_adjtimex, sys_adjtimex)
 
-#define __NR_setrlimit                         160
+#define __NR_setrlimit                          160
 __SYSCALL(__NR_setrlimit, sys_setrlimit)
 
-#define __NR_chroot                            161
+#define __NR_chroot                             161
 __SYSCALL(__NR_chroot, sys_chroot)
 
-#define __NR_sync                              162
+#define __NR_sync                               162
 __SYSCALL(__NR_sync, sys_sync)
 
-#define __NR_acct                              163
+#define __NR_acct                               163
 __SYSCALL(__NR_acct, sys_acct)
 
-#define __NR_settimeofday                      164
+#define __NR_settimeofday                       164
 __SYSCALL(__NR_settimeofday, sys_settimeofday)
 
-#define __NR_mount                             165
+#define __NR_mount                              165
 __SYSCALL(__NR_mount, sys_mount)
-#define __NR_umount2                           166
+#define __NR_umount2                            166
 __SYSCALL(__NR_umount2, sys_umount)
 
-#define __NR_swapon                            167
+#define __NR_swapon                             167
 __SYSCALL(__NR_swapon, sys_swapon)
-#define __NR_swapoff                           168
+#define __NR_swapoff                            168
 __SYSCALL(__NR_swapoff, sys_swapoff)
 
-#define __NR_reboot                            169
+#define __NR_reboot                             169
 __SYSCALL(__NR_reboot, sys_reboot)
 
-#define __NR_sethostname                       170
+#define __NR_sethostname                        170
 __SYSCALL(__NR_sethostname, sys_sethostname)
-#define __NR_setdomainname                     171
+#define __NR_setdomainname                      171
 __SYSCALL(__NR_setdomainname, sys_setdomainname)
 
-#define __NR_iopl                              172
+#define __NR_iopl                               172
 __SYSCALL(__NR_iopl, stub_iopl)
-#define __NR_ioperm                            173
+#define __NR_ioperm                             173
 __SYSCALL(__NR_ioperm, sys_ioperm)
 
-#define __NR_create_module                     174
+#define __NR_create_module                      174
 __SYSCALL(__NR_create_module, sys_ni_syscall)
-#define __NR_init_module                       175
+#define __NR_init_module                        175
 __SYSCALL(__NR_init_module, sys_init_module)
-#define __NR_delete_module                     176
+#define __NR_delete_module                      176
 __SYSCALL(__NR_delete_module, sys_delete_module)
-#define __NR_get_kernel_syms                   177
+#define __NR_get_kernel_syms                    177
 __SYSCALL(__NR_get_kernel_syms, sys_ni_syscall)
-#define __NR_query_module                      178
+#define __NR_query_module                       178
 __SYSCALL(__NR_query_module, sys_ni_syscall)
 
-#define __NR_quotactl                          179
+#define __NR_quotactl                           179
 __SYSCALL(__NR_quotactl, sys_quotactl)
 
-#define __NR_nfsservctl                        180
+#define __NR_nfsservctl                         180
 __SYSCALL(__NR_nfsservctl, sys_nfsservctl)
 
-#define __NR_getpmsg                           181      /* reserved for LiS/STREAMS */
+/* reserved for LiS/STREAMS */
+#define __NR_getpmsg                            181
 __SYSCALL(__NR_getpmsg, sys_ni_syscall)
-#define __NR_putpmsg                           182      /* reserved for LiS/STREAMS */
+#define __NR_putpmsg                            182
 __SYSCALL(__NR_putpmsg, sys_ni_syscall)
 
-#define __NR_afs_syscall                       183      /* reserved for AFS */ 
+/* reserved for AFS */
+#define __NR_afs_syscall                        183
 __SYSCALL(__NR_afs_syscall, sys_ni_syscall)
 
-#define __NR_tuxcall                    184 /* reserved for tux */
+/* reserved for tux */
+#define __NR_tuxcall                            184
 __SYSCALL(__NR_tuxcall, sys_ni_syscall)
 
-#define __NR_security                   185
+#define __NR_security                           185
 __SYSCALL(__NR_security, sys_ni_syscall)
 
-#define __NR_gettid             186
+#define __NR_gettid                             186
 __SYSCALL(__NR_gettid, sys_gettid)
 
-#define __NR_readahead          187
+#define __NR_readahead                          187
 __SYSCALL(__NR_readahead, sys_readahead)
-#define __NR_setxattr           188
+#define __NR_setxattr                           188
 __SYSCALL(__NR_setxattr, sys_setxattr)
-#define __NR_lsetxattr          189
+#define __NR_lsetxattr                          189
 __SYSCALL(__NR_lsetxattr, sys_lsetxattr)
-#define __NR_fsetxattr          190
+#define __NR_fsetxattr                          190
 __SYSCALL(__NR_fsetxattr, sys_fsetxattr)
-#define __NR_getxattr           191
+#define __NR_getxattr                           191
 __SYSCALL(__NR_getxattr, sys_getxattr)
-#define __NR_lgetxattr          192
+#define __NR_lgetxattr                          192
 __SYSCALL(__NR_lgetxattr, sys_lgetxattr)
-#define __NR_fgetxattr          193
-__SYSCALL(__NR_fgetxattr, sys_fgetxattr) 
-#define __NR_listxattr          194
-__SYSCALL(__NR_listxattr, sys_listxattr) 
-#define __NR_llistxattr         195
-__SYSCALL(__NR_llistxattr, sys_llistxattr) 
-#define __NR_flistxattr         196
-__SYSCALL(__NR_flistxattr, sys_flistxattr) 
-#define __NR_removexattr        197
-__SYSCALL(__NR_removexattr, sys_removexattr) 
-#define __NR_lremovexattr       198
-__SYSCALL(__NR_lremovexattr, sys_lremovexattr) 
-#define __NR_fremovexattr       199
-__SYSCALL(__NR_fremovexattr, sys_fremovexattr) 
-#define __NR_tkill      200
-__SYSCALL(__NR_tkill, sys_tkill) 
-#define __NR_time      201
+#define __NR_fgetxattr                          193
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr                          194
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr                         195
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr                         196
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr                        197
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr                       198
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr                       199
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_tkill                              200
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_time                               201
 __SYSCALL(__NR_time, sys_time)
-#define __NR_futex     202
+#define __NR_futex                              202
 __SYSCALL(__NR_futex, sys_futex)
-#define __NR_sched_setaffinity    203
+#define __NR_sched_setaffinity                  203
 __SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
-#define __NR_sched_getaffinity     204
+#define __NR_sched_getaffinity                  204
 __SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
-#define __NR_set_thread_area    205
+#define __NR_set_thread_area                    205
 __SYSCALL(__NR_set_thread_area, sys_ni_syscall) /* use arch_prctl */
-#define __NR_io_setup   206
+#define __NR_io_setup                           206
 __SYSCALL(__NR_io_setup, sys_io_setup)
-#define __NR_io_destroy 207
+#define __NR_io_destroy                         207
 __SYSCALL(__NR_io_destroy, sys_io_destroy)
-#define __NR_io_getevents       208
+#define __NR_io_getevents                       208
 __SYSCALL(__NR_io_getevents, sys_io_getevents)
-#define __NR_io_submit  209
+#define __NR_io_submit                          209
 __SYSCALL(__NR_io_submit, sys_io_submit)
-#define __NR_io_cancel  210
+#define __NR_io_cancel                          210
 __SYSCALL(__NR_io_cancel, sys_io_cancel)
-#define __NR_get_thread_area    211
+#define __NR_get_thread_area                    211
 __SYSCALL(__NR_get_thread_area, sys_ni_syscall) /* use arch_prctl */
-#define __NR_lookup_dcookie     212
+#define __NR_lookup_dcookie                     212
 __SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
-#define __NR_epoll_create       213
+#define __NR_epoll_create                       213
 __SYSCALL(__NR_epoll_create, sys_epoll_create)
-#define __NR_epoll_ctl_old      214
+#define __NR_epoll_ctl_old                      214
 __SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall)
-#define __NR_epoll_wait_old     215
+#define __NR_epoll_wait_old                     215
 __SYSCALL(__NR_epoll_wait_old, sys_ni_syscall)
-#define __NR_remap_file_pages   216
+#define __NR_remap_file_pages                   216
 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
-#define __NR_getdents64 217
+#define __NR_getdents64                         217
 __SYSCALL(__NR_getdents64, sys_getdents64)
-#define __NR_set_tid_address    218
+#define __NR_set_tid_address                    218
 __SYSCALL(__NR_set_tid_address, sys_set_tid_address)
-#define __NR_restart_syscall    219
+#define __NR_restart_syscall                    219
 __SYSCALL(__NR_restart_syscall, sys_restart_syscall)
-#define __NR_semtimedop         220
+#define __NR_semtimedop                         220
 __SYSCALL(__NR_semtimedop, sys_semtimedop)
-#define __NR_fadvise64          221
+#define __NR_fadvise64                          221
 __SYSCALL(__NR_fadvise64, sys_fadvise64)
-#define __NR_timer_create               222
+#define __NR_timer_create                       222
 __SYSCALL(__NR_timer_create, sys_timer_create)
-#define __NR_timer_settime              223
+#define __NR_timer_settime                      223
 __SYSCALL(__NR_timer_settime, sys_timer_settime)
-#define __NR_timer_gettime              224
+#define __NR_timer_gettime                      224
 __SYSCALL(__NR_timer_gettime, sys_timer_gettime)
-#define __NR_timer_getoverrun           225
+#define __NR_timer_getoverrun                   225
 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
-#define __NR_timer_delete       226
+#define __NR_timer_delete                       226
 __SYSCALL(__NR_timer_delete, sys_timer_delete)
-#define __NR_clock_settime      227
+#define __NR_clock_settime                      227
 __SYSCALL(__NR_clock_settime, sys_clock_settime)
-#define __NR_clock_gettime      228
+#define __NR_clock_gettime                      228
 __SYSCALL(__NR_clock_gettime, sys_clock_gettime)
-#define __NR_clock_getres       229
+#define __NR_clock_getres                       229
 __SYSCALL(__NR_clock_getres, sys_clock_getres)
-#define __NR_clock_nanosleep    230
+#define __NR_clock_nanosleep                    230
 __SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
-#define __NR_exit_group         231
+#define __NR_exit_group                         231
 __SYSCALL(__NR_exit_group, sys_exit_group)
-#define __NR_epoll_wait         232
+#define __NR_epoll_wait                         232
 __SYSCALL(__NR_epoll_wait, sys_epoll_wait)
-#define __NR_epoll_ctl          233
+#define __NR_epoll_ctl                          233
 __SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
-#define __NR_tgkill             234
+#define __NR_tgkill                             234
 __SYSCALL(__NR_tgkill, sys_tgkill)
-#define __NR_utimes             235
+#define __NR_utimes                             235
 __SYSCALL(__NR_utimes, sys_utimes)
-#define __NR_vserver            236
+#define __NR_vserver                            236
 __SYSCALL(__NR_vserver, sys_ni_syscall)
-#define __NR_mbind              237
+#define __NR_mbind                              237
 __SYSCALL(__NR_mbind, sys_mbind)
-#define __NR_set_mempolicy      238
+#define __NR_set_mempolicy                      238
 __SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
-#define __NR_get_mempolicy      239
+#define __NR_get_mempolicy                      239
 __SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
-#define __NR_mq_open            240
+#define __NR_mq_open                            240
 __SYSCALL(__NR_mq_open, sys_mq_open)
-#define __NR_mq_unlink          241
+#define __NR_mq_unlink                          241
 __SYSCALL(__NR_mq_unlink, sys_mq_unlink)
-#define __NR_mq_timedsend       242
+#define __NR_mq_timedsend                       242
 __SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
-#define __NR_mq_timedreceive    243
+#define __NR_mq_timedreceive                    243
 __SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
-#define __NR_mq_notify          244
+#define __NR_mq_notify                          244
 __SYSCALL(__NR_mq_notify, sys_mq_notify)
-#define __NR_mq_getsetattr      245
+#define __NR_mq_getsetattr                      245
 __SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
-#define __NR_kexec_load         246
+#define __NR_kexec_load                         246
 __SYSCALL(__NR_kexec_load, sys_kexec_load)
-#define __NR_waitid             247
+#define __NR_waitid                             247
 __SYSCALL(__NR_waitid, sys_waitid)
-#define __NR_add_key            248
+#define __NR_add_key                            248
 __SYSCALL(__NR_add_key, sys_add_key)
-#define __NR_request_key        249
+#define __NR_request_key                        249
 __SYSCALL(__NR_request_key, sys_request_key)
-#define __NR_keyctl             250
+#define __NR_keyctl                             250
 __SYSCALL(__NR_keyctl, sys_keyctl)
-#define __NR_ioprio_set         251
+#define __NR_ioprio_set                         251
 __SYSCALL(__NR_ioprio_set, sys_ioprio_set)
-#define __NR_ioprio_get         252
+#define __NR_ioprio_get                         252
 __SYSCALL(__NR_ioprio_get, sys_ioprio_get)
-#define __NR_inotify_init       253
+#define __NR_inotify_init                       253
 __SYSCALL(__NR_inotify_init, sys_inotify_init)
-#define __NR_inotify_add_watch  254
+#define __NR_inotify_add_watch                  254
 __SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
-#define __NR_inotify_rm_watch   255
+#define __NR_inotify_rm_watch                   255
 __SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
-#define __NR_migrate_pages      256
+#define __NR_migrate_pages                      256
 __SYSCALL(__NR_migrate_pages, sys_migrate_pages)
-#define __NR_openat             257
+#define __NR_openat                             257
 __SYSCALL(__NR_openat, sys_openat)
-#define __NR_mkdirat            258
+#define __NR_mkdirat                            258
 __SYSCALL(__NR_mkdirat, sys_mkdirat)
-#define __NR_mknodat            259
+#define __NR_mknodat                            259
 __SYSCALL(__NR_mknodat, sys_mknodat)
-#define __NR_fchownat           260
+#define __NR_fchownat                           260
 __SYSCALL(__NR_fchownat, sys_fchownat)
-#define __NR_futimesat          261
+#define __NR_futimesat                          261
 __SYSCALL(__NR_futimesat, sys_futimesat)
-#define __NR_newfstatat         262
+#define __NR_newfstatat                         262
 __SYSCALL(__NR_newfstatat, sys_newfstatat)
-#define __NR_unlinkat           263
+#define __NR_unlinkat                           263
 __SYSCALL(__NR_unlinkat, sys_unlinkat)
-#define __NR_renameat           264
+#define __NR_renameat                           264
 __SYSCALL(__NR_renameat, sys_renameat)
-#define __NR_linkat             265
+#define __NR_linkat                             265
 __SYSCALL(__NR_linkat, sys_linkat)
-#define __NR_symlinkat          266
+#define __NR_symlinkat                          266
 __SYSCALL(__NR_symlinkat, sys_symlinkat)
-#define __NR_readlinkat         267
+#define __NR_readlinkat                         267
 __SYSCALL(__NR_readlinkat, sys_readlinkat)
-#define __NR_fchmodat           268
+#define __NR_fchmodat                           268
 __SYSCALL(__NR_fchmodat, sys_fchmodat)
-#define __NR_faccessat          269
+#define __NR_faccessat                          269
 __SYSCALL(__NR_faccessat, sys_faccessat)
-#define __NR_pselect6           270
+#define __NR_pselect6                           270
 __SYSCALL(__NR_pselect6, sys_pselect6)
-#define __NR_ppoll              271
+#define __NR_ppoll                              271
 __SYSCALL(__NR_ppoll,   sys_ppoll)
-#define __NR_unshare            272
+#define __NR_unshare                            272
 __SYSCALL(__NR_unshare, sys_unshare)
-#define __NR_set_robust_list    273
+#define __NR_set_robust_list                    273
 __SYSCALL(__NR_set_robust_list, sys_set_robust_list)
-#define __NR_get_robust_list    274
+#define __NR_get_robust_list                    274
 __SYSCALL(__NR_get_robust_list, sys_get_robust_list)
-#define __NR_splice             275
+#define __NR_splice                             275
 __SYSCALL(__NR_splice, sys_splice)
-#define __NR_tee                276
+#define __NR_tee                                276
 __SYSCALL(__NR_tee, sys_tee)
-#define __NR_sync_file_range    277
+#define __NR_sync_file_range                    277
 __SYSCALL(__NR_sync_file_range, sys_sync_file_range)
-#define __NR_vmsplice           278
+#define __NR_vmsplice                           278
 __SYSCALL(__NR_vmsplice, sys_vmsplice)
-#define __NR_move_pages         279
+#define __NR_move_pages                         279
 __SYSCALL(__NR_move_pages, sys_move_pages)
-#define __NR_utimensat          280
+#define __NR_utimensat                          280
 __SYSCALL(__NR_utimensat, sys_utimensat)
 #define __IGNORE_getcpu         /* implemented as a vsyscall */
-#define __NR_epoll_pwait        281
+#define __NR_epoll_pwait                        281
 __SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
-#define __NR_signalfd           282
+#define __NR_signalfd                           282
 __SYSCALL(__NR_signalfd, sys_signalfd)
-#define __NR_timerfd            283
+#define __NR_timerfd                            283
 __SYSCALL(__NR_timerfd, sys_timerfd)
-#define __NR_eventfd            284
+#define __NR_eventfd                            284
 __SYSCALL(__NR_eventfd, sys_eventfd)
-#define __NR_fallocate          285
+#define __NR_fallocate                          285
 __SYSCALL(__NR_fallocate, sys_fallocate)
 
 #ifndef __NO_STUBS
@@ -656,26 +659,9 @@ __SYSCALL(__NR_fallocate, sys_fallocate)
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_TIME
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/linkage.h>
-#include <linux/compiler.h>
-#include <linux/types.h>
-#include <asm/ptrace.h>
-
-asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs);
-struct sigaction;
-asmlinkage long sys_rt_sigaction(int sig,
-                                const struct sigaction __user *act,
-                                struct sigaction __user *oact,
-                                size_t sigsetsize);
-
-#endif  /* __ASSEMBLY__ */
-#endif  /* __KERNEL__ */
 #endif  /* __NO_STUBS */
 
+#ifdef __KERNEL__
 /*
  * "Conditional" syscalls
  *
@@ -683,5 +669,6 @@ asmlinkage long sys_rt_sigaction(int sig,
  * but it doesn't work on all toolchains, so we just do it by hand
  */
 #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#endif  /* __KERNEL__ */
 
 #endif /* _ASM_X86_64_UNISTD_H_ */
diff --git a/include/asm-x86/unwind.h b/include/asm-x86/unwind.h
index 7e4d7ad55208..8b064bd9c553 100644
--- a/include/asm-x86/unwind.h
+++ b/include/asm-x86/unwind.h
@@ -1,5 +1,13 @@
-#ifdef CONFIG_X86_32
-# include "unwind_32.h"
-#else
-# include "unwind_64.h"
-#endif
+#ifndef _ASM_X86_UNWIND_H
+#define _ASM_X86_UNWIND_H
+
+#define UNW_PC(frame) ((void)(frame), 0UL)
+#define UNW_SP(frame) ((void)(frame), 0UL)
+#define UNW_FP(frame) ((void)(frame), 0UL)
+
+static inline int arch_unw_user_mode(const void *info)
+{
+        return 0;
+}
+
+#endif /* _ASM_X86_UNWIND_H */
diff --git a/include/asm-x86/unwind_32.h b/include/asm-x86/unwind_32.h
deleted file mode 100644
index 43c70c3de2f9..000000000000
--- a/include/asm-x86/unwind_32.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ASM_I386_UNWIND_H
-#define _ASM_I386_UNWIND_H
-
-#define UNW_PC(frame) ((void)(frame), 0)
-#define UNW_SP(frame) ((void)(frame), 0)
-#define UNW_FP(frame) ((void)(frame), 0)
-
-static inline int arch_unw_user_mode(const void *info)
-{
-        return 0;
-}
-
-#endif /* _ASM_I386_UNWIND_H */
diff --git a/include/asm-x86/unwind_64.h b/include/asm-x86/unwind_64.h
deleted file mode 100644
index 02710f6a4560..000000000000
--- a/include/asm-x86/unwind_64.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_64_UNWIND_H
-#define _ASM_X86_64_UNWIND_H
-
-#define UNW_PC(frame) ((void)(frame), 0UL)
-#define UNW_SP(frame) ((void)(frame), 0UL)
-
-static inline int arch_unw_user_mode(const void *info)
-{
-        return 0;
-}
-
-#endif /* _ASM_X86_64_UNWIND_H */
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 09306d47ff5e..ea1bf5ba092f 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -19,5 +19,11 @@
 #define SDIO_CLASS_WLAN         0x07    /* WLAN interface */
 #define SDIO_CLASS_ATA          0x08    /* Embedded SDIO-ATA std interface */
 
+/*
+ * Vendors and devices.  Sort key: vendor first, device next.
+ */
+
+#define SDIO_VENDOR_ID_MARVELL                  0x02df
+#define SDIO_DEVICE_ID_MARVELL_LIBERTAS         0x9103
 
 #endif
diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h
index ff61ea365997..b05d8a6d9143 100644
--- a/include/xen/interface/vcpu.h
+++ b/include/xen/interface/vcpu.h
@@ -160,8 +160,9 @@ struct vcpu_set_singleshot_timer {
  */
 #define VCPUOP_register_vcpu_info   10  /* arg == struct vcpu_info */
 struct vcpu_register_vcpu_info {
-    uint32_t mfn;               /* mfn of page to place vcpu_info */
-    uint32_t offset;            /* offset within page */
+    uint64_t mfn;    /* mfn of page to place vcpu_info */
+    uint32_t offset; /* offset within page */
+    uint32_t rsvd;   /* unused */
 };
 
 #endif /* __XEN_PUBLIC_VCPU_H__ */
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index fab9dd8bbd6b..8cfb8b2ce773 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -222,20 +222,8 @@ static void tick_do_broadcast_on_off(void *why)
         if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
                 goto out;
 
-        /*
-         * Defect device ?
-         */
-        if (!tick_device_is_functional(dev)) {
-                /*
-                 * AMD C1E wreckage fixup:
-                 *
-                 * Device was registered functional in the first
-                 * place. Now the secondary CPU detected the C1E
-                 * misfeature and notifies us to fix it up
-                 */
-                if (*reason != CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
-                        goto out;
-        }
+        if (!tick_device_is_functional(dev))
+                goto out;
 
         switch (*reason) {
         case CLOCK_EVT_NOTIFY_BROADCAST_ON:
@@ -246,6 +234,8 @@ static void tick_do_broadcast_on_off(void *why)
                                 clockevents_set_mode(dev,
                                                      CLOCK_EVT_MODE_SHUTDOWN);
                 }
+                if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
+                        dev->features |= CLOCK_EVT_FEAT_DUMMY;
                 break;
         case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
                 if (cpu_isset(cpu, tick_broadcast_mask)) {
diff --git a/mm/Kconfig b/mm/Kconfig
index 1cc6cada2bbf..b1f03b0eb7f1 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -155,7 +155,6 @@ config SPLIT_PTLOCK_CPUS
         int
         default "4096" if ARM && !CPU_CACHE_VIPT
         default "4096" if PARISC && !PA20
-        default "4096" if XEN
         default "4"
 
 #