Merge branch 'x86/core' into x86/headers

107 files changed, 1776 insertions, 2978 deletions

diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index 37822206083..bb70e397aa8 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -23,8 +23,6 @@
  */
 static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 {
-	u16 gs;
-
 /* changed the size calculations - should hopefully work better. lbt */
 	dump->magic = CMAGIC;
 	dump->start_code = 0;
@@ -57,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 	dump->regs.ds = (u16)regs->ds;
 	dump->regs.es = (u16)regs->es;
 	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs, gs);
+	dump->regs.gs = get_user_gs(regs);
 	dump->regs.orig_ax = regs->orig_ax;
 	dump->regs.ip = regs->ip;
 	dump->regs.cs = (u16)regs->cs;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 9830681446a..4518dc50090 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -102,9 +102,6 @@ static inline void disable_acpi(void)
 	acpi_noirq = 1;
 }
 
-/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
-#define FIX_ACPI_PAGES 4
-
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ab1d51a8855..fba49f66228 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -33,7 +33,13 @@
 	} while (0)
 
 
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
 extern void generic_apic_probe(void);
+#else
+static inline void generic_apic_probe(void)
+{
+}
+#endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
@@ -41,6 +47,21 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
+
+#ifdef CONFIG_SMP
+extern void __inquire_remote_apic(int apicid);
+#else /* CONFIG_SMP */
+static inline void __inquire_remote_apic(int apicid)
+{
+}
+#endif /* CONFIG_SMP */
+
+static inline void default_inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
+
 /*
  * Basic functions accessing APICs.
  */
@@ -124,12 +145,35 @@ struct apic_ops {
 
 extern struct apic_ops *apic_ops;
 
-#define apic_read (apic_ops->read)
-#define apic_write (apic_ops->write)
-#define apic_icr_read (apic_ops->icr_read)
-#define apic_icr_write (apic_ops->icr_write)
-#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
-#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+static inline u32 apic_read(u32 reg)
+{
+	return apic_ops->read(reg);
+}
+
+static inline void apic_write(u32 reg, u32 val)
+{
+	apic_ops->write(reg, val);
+}
+
+static inline u64 apic_icr_read(void)
+{
+	return apic_ops->icr_read();
+}
+
+static inline void apic_icr_write(u32 low, u32 high)
+{
+	apic_ops->icr_write(low, high);
+}
+
+static inline void apic_wait_icr_idle(void)
+{
+	apic_ops->wait_icr_idle();
+}
+
+static inline u32 safe_apic_wait_icr_idle(void)
+{
+	return apic_ops->safe_wait_icr_idle();
+}
 
 extern int get_physical_broadcast(void);
 
@@ -196,4 +240,22 @@ static inline void disable_local_APIC(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_X86_64
+#define	SET_APIC_ID(x)		(apic->set_apic_id(x))
+#else
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static inline unsigned default_get_apic_id(unsigned long x)
+{
+	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+
+	if (APIC_XAPIC(ver))
+		return (x >> 24) & 0xFF;
+	else
+		return (x >> 24) & 0x0F;
+}
+#endif
+
+#endif
+
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 00000000000..82f613c607c
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/mach-default/apm.h b/arch/x86/include/asm/apm.h
index 20370c6db74..20370c6db74 100644
--- a/arch/x86/include/asm/mach-default/apm.h
+++ b/arch/x86/include/asm/apm.h
diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h
deleted file mode 100644
index d8dd9f53791..00000000000
--- a/arch/x86/include/asm/bigsmp/apic.h
+++ /dev/null
@@ -1,155 +0,0 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	return (1);
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-#ifdef CONFIG_SMP
-	return &cpu_online_map;
-#else
-	return &cpumask_of_cpu(0);
-#endif
-}
-
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target proc */
-#define NO_BALANCE_IRQ		(0)
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return (0);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-	return (1);
-}
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long val, id;
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	id = xapic_phys_to_log_apicid(cpu);
-	val |= SET_APIC_LOGICAL_ID(id);
-	return val;
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-		"Physflat", nr_ioapics);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return (0);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return apicid_2_node[hard_smp_processor_id()];
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < nr_cpu_ids)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-
-	return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	return physid_mask_of_physid(phys_apicid);
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_physical_id(cpu);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xFFL);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return (1);
-}
-
-/* As we are using single CPU as destination, pick only one CPU here */
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	int cpu;
-	int apicid;	
-
-	cpu = first_cpu(*cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-						  const struct cpumask *andmask)
-{
-	int cpu;
-
-	/*
-	 * We're using fixed IRQ delivery, can only return one phys APIC ID.
-	 * May as well be the first.
-	 */
-	for_each_cpu_and(cpu, cpumask, andmask)
-		if (cpumask_test_cpu(cpu, cpu_online_mask))
-			break;
-	if (cpu < nr_cpu_ids)
-		return cpu_to_logical_apicid(cpu);
-
-	return BAD_APICID;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */
diff --git a/arch/x86/include/asm/bigsmp/apicdef.h b/arch/x86/include/asm/bigsmp/apicdef.h
deleted file mode 100644
index 392c3f5ef2f..00000000000
--- a/arch/x86/include/asm/bigsmp/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/bigsmp/ipi.h b/arch/x86/include/asm/bigsmp/ipi.h
deleted file mode 100644
index 27fcd01b3ae..00000000000
--- a/arch/x86/include/asm/bigsmp/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_MACH_IPI_H */
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 2bc162e0ec6..0e63c9a2a8d 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -1,5 +1,55 @@
 /*
- * Some macros to handle stack frames in assembly.
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+  arguments           |  callee-saved      | extra caller-saved | return
+ [callee-clobbered]   |                    | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11             | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+   functions when it sees tail-call optimization possibilities) rflags is
+   clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*]  In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+      bit more complex: up to 128 bits width we return small structures
+      straight in rax, rdx. For structures larger than that (3 words or
+      larger) the caller puts a pointer to an on-stack return struct
+      [allocated in the caller's stack frame] into the first argument - i.e.
+      into rdi. All other arguments shift up by one in this case.
+      Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+  arguments         | callee-saved        | extra caller-saved | return
+ [callee-clobbered] |                     | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx        | ebx edi esi ebp [*] | <none>             | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+   is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*]  In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+      semantics as on 64-bit: edx can be used for a second return value
+      (i.e. covering integer and structure sizes up to 64 bits) - after that
+      it gets more complex and more expensive: 3-word or larger struct returns
+      get done in the caller's frame and the pointer to the return struct goes
+      into regparm0, i.e. eax - the other arguments shift up and the
+      function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
  */
 
 #define R15		  0
@@ -9,7 +59,7 @@
 #define RBP		 32
 #define RBX		 40
 
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here: */
 #define R11		 48
 #define R10		 56
 #define R9		 64
@@ -22,7 +72,7 @@
 #define ORIG_RAX	120       /* + error_code */
 /* end of arguments */
 
-/* cpu exception frame or undefined in case of fast syscall. */
+/* cpu exception frame or undefined in case of fast syscall: */
 #define RIP		128
 #define CS		136
 #define EFLAGS		144
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bae482df603..b185091bf19 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -7,6 +7,20 @@
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
 
+#ifdef CONFIG_SMP
+
+extern void prefill_possible_map(void);
+
+#else /* CONFIG_SMP */
+
+static inline void prefill_possible_map(void) {}
+
+#define cpu_physical_id(cpu)			boot_cpu_physical_apicid
+#define safe_smp_processor_id()			0
+#define stack_smp_processor_id()		0
+
+#endif /* CONFIG_SMP */
+
 struct x86_cpu {
 	struct cpu cpu;
 };
@@ -17,4 +31,7 @@ extern void arch_unregister_cpu(int);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
+
+extern unsigned int boot_cpu_id;
+
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea408dcba51..7301e60dc4a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -93,6 +93,7 @@
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
new file mode 100644
index 00000000000..a7f3c75f8ad
--- /dev/null
+++ b/arch/x86/include/asm/cpumask.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_CPUMASK_H
+#define _ASM_X86_CPUMASK_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+extern void setup_cpu_local_masks(void);
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
+
+static inline void setup_cpu_local_masks(void) { }
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f8d67..c68c361697e 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -1,39 +1,21 @@
 #ifndef _ASM_X86_CURRENT_H
 #define _ASM_X86_CURRENT_H
 
-#ifdef CONFIG_X86_32
 #include <linux/compiler.h>
 #include <asm/percpu.h>
 
+#ifndef __ASSEMBLY__
 struct task_struct;
 
 DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-	return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return read_pda(pcurrent);
+	return percpu_read(current_task);
 }
 
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+#define current get_current()
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* X86_32 */
-
-#define current get_current()
-
 #endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/mach-default/do_timer.h b/arch/x86/include/asm/do_timer.h
index 23ecda0b28a..23ecda0b28a 100644
--- a/arch/x86/include/asm/mach-default/do_timer.h
+++ b/arch/x86/include/asm/do_timer.h
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f51a3ddde01..83c1bc8d2e8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -112,7 +112,7 @@ extern unsigned int vdso_enabled;
  * now struct_user_regs, they are different)
  */
 
-#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
+#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs)	\
 do {						\
 	pr_reg[0] = regs->bx;			\
 	pr_reg[1] = regs->cx;			\
@@ -124,7 +124,6 @@ do {						\
 	pr_reg[7] = regs->ds & 0xffff;		\
 	pr_reg[8] = regs->es & 0xffff;		\
 	pr_reg[9] = regs->fs & 0xffff;		\
-	savesegment(gs, pr_reg[10]);		\
 	pr_reg[11] = regs->orig_ax;		\
 	pr_reg[12] = regs->ip;			\
 	pr_reg[13] = regs->cs & 0xffff;		\
@@ -133,6 +132,18 @@ do {						\
 	pr_reg[16] = regs->ss & 0xffff;		\
 } while (0);
 
+#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
+do {						\
+	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+	pr_reg[10] = get_user_gs(regs);		\
+} while (0);
+
+#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs)	\
+do {						\
+	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+	savesegment(gs, pr_reg[10]);		\
+} while (0);
+
 #define ELF_PLATFORM	(utsname()->machine)
 #define set_personality_64bit()	do { } while (0)
 
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 6b1add8e31d..854d538ae85 100644
--- a/arch/x86/include/asm/mach-default/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -9,12 +9,28 @@
  * is no hardware IRQ pin equivalent for them, they are triggered
  * through the ICC by us (IPIs)
  */
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+
+BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+		 smp_invalidate_interrupt)
 #endif
 
 /*
@@ -25,10 +41,15 @@ BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
  * a much simpler SMP time architecture:
  */
 #ifdef CONFIG_X86_LOCAL_APIC
+
 BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
+#ifdef CONFIG_PERF_COUNTERS
+BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+#endif
+
 #ifdef CONFIG_X86_MCE_P4THERMAL
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
deleted file mode 100644
index c58b9cc7446..00000000000
--- a/arch/x86/include/asm/es7000/apic.h
+++ /dev/null
@@ -1,242 +0,0 @@
-#ifndef __ASM_ES7000_APIC_H
-#define __ASM_ES7000_APIC_H
-
-#include <linux/gfp.h>
-
-#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	        return (1);
-}
-
-static inline const cpumask_t *target_cpus_cluster(void)
-{
-	return &CPU_MASK_ALL;
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-	return &cpumask_of_cpu(smp_processor_id());
-}
-
-#define APIC_DFR_VALUE_CLUSTER		(APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE_CLUSTER	(dest_LowestPrio)
-#define INT_DEST_MODE_CLUSTER		(1) /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ_CLUSTER		(1)
-
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target procs */
-#define NO_BALANCE_IRQ		(0)
-#undef  APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0x0
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return 0;
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long id;
-	id = xapic_phys_to_log_apicid(cpu);
-	return (SET_APIC_LOGICAL_ID(id));
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LdR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr_cluster(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-extern int apic_version [MAX_APICS];
-static inline void setup_apic_routing(void)
-{
-	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
-	printk("Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
-		(apic_version[apic] == 0x14) ?
-			"Physical Cluster" : "Logical Cluster",
-			nr_ioapics, cpus_addr(*target_cpus())[0]);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return 0;
-}
-
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (!mps_cpu)
-		return boot_cpu_physical_apicid;
-	else if (mps_cpu < nr_cpu_ids)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	static int id = 0;
-	physid_mask_t mask;
-	mask = physid_mask_of_physid(id);
-	++id;
-	return mask;
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xff);
-}
-
-
-static inline void setup_portio_remap(void)
-{
-}
-
-extern unsigned int boot_cpu_physical_apicid;
-static inline int check_phys_apicid_present(int cpu_physical_apicid)
-{
-	boot_cpu_physical_apicid = read_apic_id();
-	return (1);
-}
-
-static inline unsigned int
-cpu_mask_to_apicid_cluster(const struct cpumask *cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpumask_weight(cpumask);
-	/* Return id to all */
-	if (num_bits_set == nr_cpu_ids)
-		return 0xFF;
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = cpumask_first(cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpumask_test_cpu(cpu, cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return 0xFF;
-			}
-			apicid = new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpus_weight(*cpumask);
-	/* Return id to all */
-	if (num_bits_set == nr_cpu_ids)
-		return cpu_to_logical_apicid(0);
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = first_cpu(*cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpu_isset(cpu, *cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return cpu_to_logical_apicid(0);
-			}
-			apicid = new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
-						  const struct cpumask *andmask)
-{
-	int apicid = cpu_to_logical_apicid(0);
-	cpumask_var_t cpumask;
-
-	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-		return apicid;
-
-	cpumask_and(cpumask, inmask, andmask);
-	cpumask_and(cpumask, cpumask, cpu_online_mask);
-	apicid = cpu_mask_to_apicid(cpumask);
-
-	free_cpumask_var(cpumask);
-	return apicid;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_ES7000_APIC_H */
diff --git a/arch/x86/include/asm/es7000/apicdef.h b/arch/x86/include/asm/es7000/apicdef.h
deleted file mode 100644
index 8b234a3cb85..00000000000
--- a/arch/x86/include/asm/es7000/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_ES7000_APICDEF_H
-#define __ASM_ES7000_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/es7000/ipi.h b/arch/x86/include/asm/es7000/ipi.h
deleted file mode 100644
index 7e8ed24d4b8..00000000000
--- a/arch/x86/include/asm/es7000/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_ES7000_IPI_H
-#define __ASM_ES7000_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_ES7000_IPI_H */
diff --git a/arch/x86/include/asm/es7000/mpparse.h b/arch/x86/include/asm/es7000/mpparse.h
deleted file mode 100644
index c1629b090ec..00000000000
--- a/arch/x86/include/asm/es7000/mpparse.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __ASM_ES7000_MPPARSE_H
-#define __ASM_ES7000_MPPARSE_H
-
-#include <linux/acpi.h>
-
-extern int parse_unisys_oem (char *oemptr);
-extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
-extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
-extern void setup_unisys(void);
-
-#ifndef CONFIG_X86_GENERICARCH
-extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
-extern int mps_oem_check(struct mpc_table *mpc, char *oem, char *productid);
-#endif
-
-#ifdef CONFIG_ACPI
-
-static inline int es7000_check_dsdt(void)
-{
-	struct acpi_table_header header;
-
-	if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
-	    !strncmp(header.oem_id, "UNISYS", 6))
-		return 1;
-	return 0;
-}
-#endif
-
-#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
deleted file mode 100644
index 78f0daaee43..00000000000
--- a/arch/x86/include/asm/es7000/wakecpu.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef __ASM_ES7000_WAKECPU_H
-#define __ASM_ES7000_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW	0x467
-#define TRAMPOLINE_PHYS_HIGH	0x469
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-#ifndef CONFIG_ES7000_CLUSTERED_APIC
-	while (!atomic_read(deassert))
-		cpu_relax();
-#endif
-	return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-extern void __inquire_remote_apic(int apicid);
-
-static inline void inquire_remote_apic(int apicid)
-{
-	if (apic_verbosity >= APIC_DEBUG)
-		__inquire_remote_apic(apicid);
-}
-
-#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
index c7115c1d721..047d9bab2b3 100644
--- a/arch/x86/include/asm/fixmap_32.h
+++ b/arch/x86/include/asm/fixmap_32.h
@@ -95,10 +95,6 @@ enum fixed_addresses {
 			(__end_of_permanent_fixed_addresses & 255),
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
 	FIX_WP_TEST,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif
diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h
index 00a30ab9b1a..298d9ba3fae 100644
--- a/arch/x86/include/asm/fixmap_64.h
+++ b/arch/x86/include/asm/fixmap_64.h
@@ -50,10 +50,6 @@ enum fixed_addresses {
 	FIX_PARAVIRT_BOOTMAP,
 #endif
 	__end_of_permanent_fixed_addresses,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif
diff --git a/arch/x86/include/asm/genapic.h b/arch/x86/include/asm/genapic.h
index d48bee663a6..273b99452ae 100644
--- a/arch/x86/include/asm/genapic.h
+++ b/arch/x86/include/asm/genapic.h
@@ -1,5 +1,263 @@
+#ifndef _ASM_X86_GENAPIC_H
+#define _ASM_X86_GENAPIC_H
+
+#include <linux/cpumask.h>
+
+#include <asm/mpspec.h>
+#include <asm/atomic.h>
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch data struct.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+struct genapic {
+	char *name;
+
+	int (*probe)(void);
+	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+	int (*apic_id_registered)(void);
+
+	u32 irq_delivery_mode;
+	u32 irq_dest_mode;
+
+	const struct cpumask *(*target_cpus)(void);
+
+	int disable_esr;
+
+	int dest_logical;
+	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+	unsigned long (*check_apicid_present)(int apicid);
+
+	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+	void (*init_apic_ldr)(void);
+
+	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
+
+	void (*setup_apic_routing)(void);
+	int (*multi_timer_check)(int apic, int irq);
+	int (*apicid_to_node)(int logical_apicid);
+	int (*cpu_to_logical_apicid)(int cpu);
+	int (*cpu_present_to_apicid)(int mps_cpu);
+	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
+	void (*setup_portio_remap)(void);
+	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+	void (*enable_apic_mode)(void);
+	int (*phys_pkg_id)(int cpuid_apic, int index_msb);
+
+	/*
+	 * When one of the next two hooks returns 1 the genapic
+	 * is switched to this. Essentially they are additional
+	 * probe functions:
+	 */
+	int (*mps_oem_check)(struct mpc_table *mpc, char *oem, char *productid);
+
+	unsigned int (*get_apic_id)(unsigned long x);
+	unsigned long (*set_apic_id)(unsigned int id);
+	unsigned long apic_id_mask;
+
+	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
+	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+					       const struct cpumask *andmask);
+
+	/* ipi */
+	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
+	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
+					 int vector);
+	void (*send_IPI_allbutself)(int vector);
+	void (*send_IPI_all)(int vector);
+	void (*send_IPI_self)(int vector);
+
+	/* wakeup_secondary_cpu */
+	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
+
+	int trampoline_phys_low;
+	int trampoline_phys_high;
+
+	void (*wait_for_init_deassert)(atomic_t *deassert);
+	void (*smp_callin_clear_local_apic)(void);
+	void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
+	void (*inquire_remote_apic)(int apicid);
+};
+
+extern struct genapic *apic;
+
+/*
+ * Warm reset vector default position:
+ */
+#define DEFAULT_TRAMPOLINE_PHYS_LOW		0x467
+#define DEFAULT_TRAMPOLINE_PHYS_HIGH		0x469
+
 #ifdef CONFIG_X86_32
-# include "genapic_32.h"
+extern void es7000_update_genapic_to_cluster(void);
 #else
-# include "genapic_64.h"
+extern struct genapic apic_flat;
+extern struct genapic apic_physflat;
+extern struct genapic apic_x2apic_cluster;
+extern struct genapic apic_x2apic_phys;
+extern int default_acpi_madt_oem_check(char *, char *);
+
+extern void apic_send_IPI_self(int vector);
+
+extern struct genapic apic_x2apic_uv_x;
+DECLARE_PER_CPU(int, x2apic_extra_bits);
+
+extern void default_setup_apic_routing(void);
+
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
 #endif
+
+static inline void default_wait_for_init_deassert(atomic_t *deassert)
+{
+	while (!atomic_read(deassert))
+		cpu_relax();
+	return;
+}
+
+extern void generic_bigsmp_probe(void);
+
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#include <asm/smp.h>
+
+#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
+
+static inline const struct cpumask *default_target_cpus(void)
+{
+#ifdef CONFIG_SMP
+	return cpu_online_mask;
+#else
+	return cpumask_of(0);
+#endif
+}
+
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+
+
+static inline unsigned int read_apic_id(void)
+{
+	unsigned int reg;
+
+	reg = apic_read(APIC_ID);
+
+	return apic->get_apic_id(reg);
+}
+
+#ifdef CONFIG_X86_64
+extern void default_setup_apic_routing(void);
+#else
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+extern void default_init_apic_ldr(void);
+
+static inline int default_apic_id_registered(void)
+{
+	return physid_isset(read_apic_id(), phys_cpu_present_map);
+}
+
+static inline unsigned int
+default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+	return cpumask_bits(cpumask)[0];
+}
+
+static inline unsigned int
+default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+			       const struct cpumask *andmask)
+{
+	unsigned long mask1 = cpumask_bits(cpumask)[0];
+	unsigned long mask2 = cpumask_bits(andmask)[0];
+	unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+
+	return (unsigned int)(mask1 & mask2 & mask3);
+}
+
+static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+static inline void default_setup_apic_routing(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+					"Flat", nr_ioapics);
+#endif
+}
+
+extern int default_apicid_to_node(int logical_apicid);
+
+#endif
+
+static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return physid_isset(apicid, bitmap);
+}
+
+static inline unsigned long default_check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
+
+static inline physid_mask_t default_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	return phys_map;
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int default_cpu_to_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
+static inline int __default_cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
+		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+	else
+		return BAD_APICID;
+}
+
+static inline int
+__default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
+}
+
+#ifdef CONFIG_X86_32
+static inline int default_cpu_present_to_apicid(int mps_cpu)
+{
+	return __default_cpu_present_to_apicid(mps_cpu);
+}
+
+static inline int
+default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+}
+#else
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+#endif
+
+static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid)
+{
+	return physid_mask_of_physid(phys_apicid);
+}
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#endif /* _ASM_X86_GENAPIC_64_H */
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
deleted file mode 100644
index 2c05b737ee2..00000000000
--- a/arch/x86/include/asm/genapic_32.h
+++ /dev/null
@@ -1,148 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_32_H
-#define _ASM_X86_GENAPIC_32_H
-
-#include <asm/mpspec.h>
-#include <asm/atomic.h>
-
-/*
- * Generic APIC driver interface.
- *
- * An straight forward mapping of the APIC related parts of the
- * x86 subarchitecture interface to a dynamic object.
- *
- * This is used by the "generic" x86 subarchitecture.
- *
- * Copyright 2003 Andi Kleen, SuSE Labs.
- */
-
-struct mpc_bus;
-struct mpc_table;
-struct mpc_cpu;
-
-struct genapic {
-	char *name;
-	int (*probe)(void);
-
-	int (*apic_id_registered)(void);
-	const struct cpumask *(*target_cpus)(void);
-	int int_delivery_mode;
-	int int_dest_mode;
-	int ESR_DISABLE;
-	int apic_destination_logical;
-	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
-	unsigned long (*check_apicid_present)(int apicid);
-	int no_balance_irq;
-	int no_ioapic_check;
-	void (*init_apic_ldr)(void);
-	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
-
-	void (*setup_apic_routing)(void);
-	int (*multi_timer_check)(int apic, int irq);
-	int (*apicid_to_node)(int logical_apicid);
-	int (*cpu_to_logical_apicid)(int cpu);
-	int (*cpu_present_to_apicid)(int mps_cpu);
-	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
-	void (*setup_portio_remap)(void);
-	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
-	void (*enable_apic_mode)(void);
-	u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
-
-	/* mpparse */
-	/* When one of the next two hooks returns 1 the genapic
-	   is switched to this. Essentially they are additional probe
-	   functions. */
-	int (*mps_oem_check)(struct mpc_table *mpc, char *oem,
-			     char *productid);
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-
-	unsigned (*get_apic_id)(unsigned long x);
-	unsigned long apic_id_mask;
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-
-#ifdef CONFIG_SMP
-	/* ipi */
-	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-					 int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-#endif
-	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-	int trampoline_phys_low;
-	int trampoline_phys_high;
-	void (*wait_for_init_deassert)(atomic_t *deassert);
-	void (*smp_callin_clear_local_apic)(void);
-	void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
-	void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
-	void (*inquire_remote_apic)(int apicid);
-};
-
-#define APICFUNC(x) .x = x,
-
-/* More functions could be probably marked IPIFUNC and save some space
-   in UP GENERICARCH kernels, but I don't have the nerve right now
-   to untangle this mess. -AK  */
-#ifdef CONFIG_SMP
-#define IPIFUNC(x) APICFUNC(x)
-#else
-#define IPIFUNC(x)
-#endif
-
-#define APIC_INIT(aname, aprobe)			\
-{							\
-	.name = aname,					\
-	.probe = aprobe,				\
-	.int_delivery_mode = INT_DELIVERY_MODE,		\
-	.int_dest_mode = INT_DEST_MODE,			\
-	.no_balance_irq = NO_BALANCE_IRQ,		\
-	.ESR_DISABLE = esr_disable,			\
-	.apic_destination_logical = APIC_DEST_LOGICAL,	\
-	APICFUNC(apic_id_registered)			\
-	APICFUNC(target_cpus)				\
-	APICFUNC(check_apicid_used)			\
-	APICFUNC(check_apicid_present)			\
-	APICFUNC(init_apic_ldr)				\
-	APICFUNC(ioapic_phys_id_map)			\
-	APICFUNC(setup_apic_routing)			\
-	APICFUNC(multi_timer_check)			\
-	APICFUNC(apicid_to_node)			\
-	APICFUNC(cpu_to_logical_apicid)			\
-	APICFUNC(cpu_present_to_apicid)			\
-	APICFUNC(apicid_to_cpu_present)			\
-	APICFUNC(setup_portio_remap)			\
-	APICFUNC(check_phys_apicid_present)		\
-	APICFUNC(mps_oem_check)				\
-	APICFUNC(get_apic_id)				\
-	.apic_id_mask = APIC_ID_MASK,			\
-	APICFUNC(cpu_mask_to_apicid)			\
-	APICFUNC(cpu_mask_to_apicid_and)		\
-	APICFUNC(vector_allocation_domain)		\
-	APICFUNC(acpi_madt_oem_check)			\
-	IPIFUNC(send_IPI_mask)				\
-	IPIFUNC(send_IPI_allbutself)			\
-	IPIFUNC(send_IPI_all)				\
-	APICFUNC(enable_apic_mode)			\
-	APICFUNC(phys_pkg_id)				\
-	.trampoline_phys_low = TRAMPOLINE_PHYS_LOW,		\
-	.trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,		\
-	APICFUNC(wait_for_init_deassert)		\
-	APICFUNC(smp_callin_clear_local_apic)		\
-	APICFUNC(store_NMI_vector)			\
-	APICFUNC(restore_NMI_vector)			\
-	APICFUNC(inquire_remote_apic)			\
-}
-
-extern struct genapic *genapic;
-extern void es7000_update_genapic_to_cluster(void);
-
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type()		UV_NONE
-#define is_uv_system()			0
-#define uv_wakeup_secondary(a, b)	1
-#define uv_system_init()		do {} while (0)
-
-
-#endif /* _ASM_X86_GENAPIC_32_H */
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
deleted file mode 100644
index adf32fb56aa..00000000000
--- a/arch/x86/include/asm/genapic_64.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_64_H
-#define _ASM_X86_GENAPIC_64_H
-
-#include <linux/cpumask.h>
-
-/*
- * Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
- *
- * Generic APIC sub-arch data struct.
- *
- * Hacked for x86-64 by James Cleverdon from i386 architecture code by
- * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
- * James Cleverdon.
- */
-
-struct genapic {
-	char *name;
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	u32 int_delivery_mode;
-	u32 int_dest_mode;
-	int (*apic_id_registered)(void);
-	const struct cpumask *(*target_cpus)(void);
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-	void (*init_apic_ldr)(void);
-	/* ipi */
-	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-					 int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-	void (*send_IPI_self)(int vector);
-	/* */
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
-	unsigned int (*phys_pkg_id)(int index_msb);
-	unsigned int (*get_apic_id)(unsigned long x);
-	unsigned long (*set_apic_id)(unsigned int id);
-	unsigned long apic_id_mask;
-	/* wakeup_secondary_cpu */
-	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-};
-
-extern struct genapic *genapic;
-
-extern struct genapic apic_flat;
-extern struct genapic apic_physflat;
-extern struct genapic apic_x2apic_cluster;
-extern struct genapic apic_x2apic_phys;
-extern int acpi_madt_oem_check(char *, char *);
-
-extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
-
-extern struct genapic apic_x2apic_uv_x;
-DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
-
-extern void setup_apic_routing(void);
-
-#endif /* _ASM_X86_GENAPIC_64_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 000787df66e..176f058e715 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -1,11 +1,52 @@
-#ifdef CONFIG_X86_32
-# include "hardirq_32.h"
-#else
-# include "hardirq_64.h"
+#ifndef _ASM_X86_HARDIRQ_H
+#define _ASM_X86_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* arch dependent */
+	unsigned int irq0_irqs;
+#ifdef CONFIG_X86_LOCAL_APIC
+	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int irq_spurious_count;
+#endif
+#ifdef CONFIG_SMP
+	unsigned int irq_resched_count;
+	unsigned int irq_call_count;
+	unsigned int irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	unsigned int irq_thermal_count;
+# ifdef CONFIG_X86_64
+	unsigned int irq_threshold_count;
+# endif
 #endif
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT
+
+#define inc_irq_stat(member)	percpu_add(irq_stat.member, 1)
+
+#define local_softirq_pending()	percpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x)	percpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x)	percpu_or(irq_stat.__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
 
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu	arch_irq_stat_cpu
 
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
+
+#endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
deleted file mode 100644
index cf7954d1405..00000000000
--- a/arch/x86/include/asm/hardirq_32.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_32_H
-#define _ASM_X86_HARDIRQ_32_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-	unsigned int __softirq_pending;
-	unsigned long idle_timestamp;
-	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);
-
-#define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
-
-#define inc_irq_stat(member)	(__get_cpu_var(irq_stat).member++)
-
-void ack_bad_irq(unsigned int irq);
-#include <linux/irq_cpustat.h>
-
-#endif /* _ASM_X86_HARDIRQ_32_H */
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
deleted file mode 100644
index b5a6b5d5670..00000000000
--- a/arch/x86/include/asm/hardirq_64.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_64_H
-#define _ASM_X86_HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-#include <asm/pda.h>
-#include <asm/apic.h>
-
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
-#define __ARCH_IRQ_STAT 1
-
-#define inc_irq_stat(member)	add_pda(member, 1)
-
-#define local_softirq_pending() read_pda(__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
-
-extern void ack_bad_irq(unsigned int irq);
-
-#endif /* _ASM_X86_HARDIRQ_64_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 8de644b6b95..370e1c83bb4 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -25,8 +25,6 @@
 #include <asm/irq.h>
 #include <asm/sections.h>
 
-#define platform_legacy_irq(irq)	((irq) < 16)
-
 /* Interrupt handlers registered during init_IRQ */
 extern void apic_timer_interrupt(void);
 extern void error_interrupt(void);
@@ -58,7 +56,7 @@ extern void make_8259A_irq(unsigned int irq);
 extern void init_8259A(int aeoi);
 
 /* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
 extern unsigned long io_apic_irqs;
 
 extern void init_VISWS_APIC_irqs(void);
@@ -67,15 +65,7 @@ extern void disable_IO_APIC(void);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
 extern void setup_ioapic_dest(void);
 
-#ifdef CONFIG_X86_64
 extern void enable_IO_APIC(void);
-#endif
-
-/* IPI functions */
-#ifdef CONFIG_X86_32
-extern void send_IPI_self(int vector);
-#endif
-extern void send_IPI(int dest, int vector);
 
 /* Statistics */
 extern atomic_t irq_err_count;
@@ -84,21 +74,11 @@ extern atomic_t irq_mis_count;
 /* EISA */
 extern void eisa_set_level_irq(unsigned int irq);
 
-/* Voyager functions */
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
 extern void smp_call_function_single_interrupt(struct pt_regs *);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index f150b1ecf92..e5a2ab44cd5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -181,7 +181,7 @@ extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				unsigned long prot_val);
-extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
+extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
 
 /*
  * early_ioremap() and early_iounmap() are for temporary early boot-time
@@ -195,5 +195,6 @@ extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
+#define IO_SPACE_LIMIT 0xffff
 
 #endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/io_32.h b/arch/x86/include/asm/io_32.h
index 2fbe7dd26bb..a299900f592 100644
--- a/arch/x86/include/asm/io_32.h
+++ b/arch/x86/include/asm/io_32.h
@@ -37,8 +37,6 @@
   *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
   */
 
-#define IO_SPACE_LIMIT 0xffff
-
 #define XQUAD_PORTIO_BASE 0xfe400000
 #define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
 
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
index 0424c07246f..244067893af 100644
--- a/arch/x86/include/asm/io_64.h
+++ b/arch/x86/include/asm/io_64.h
@@ -136,8 +136,6 @@ __OUTS(b)
 __OUTS(w)
 __OUTS(l)
 
-#define IO_SPACE_LIMIT 0xffff
-
 #if defined(__KERNEL__) && defined(__x86_64__)
 
 #include <linux/vmalloc.h>
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7a1f44ac1f1..59cb4a1317b 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -114,38 +114,16 @@ struct IR_IO_APIC_route_entry {
 extern int nr_ioapics;
 extern int nr_ioapic_registers[MAX_IO_APICS];
 
-/*
- * MP-BIOS irq configuration table structures:
- */
-
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_config_ioapic {
-	unsigned long mp_apicaddr;
-	unsigned int mp_apicid;
-	unsigned char mp_type;
-	unsigned char mp_apicver;
-	unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
-	unsigned int mp_dstapic;
-	unsigned char mp_type;
-	unsigned char mp_irqtype;
-	unsigned short mp_irqflag;
-	unsigned char mp_srcbus;
-	unsigned char mp_srcbusirq;
-	unsigned char mp_dstirq;
-};
-
 /* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
@@ -165,15 +143,6 @@ extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
-static inline void disable_ioapic_setup(void)
-{
-#ifdef CONFIG_PCI
-	noioapicquirk = 1;
-	noioapicreroute = -1;
-#endif
-	skip_ioapic_setup = 1;
-}
-
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -200,6 +169,12 @@ extern void reinit_intr_remapped_IO_APIC(int);
 
 extern void probe_nr_irqs_gsi(void);
 
+extern int setup_ioapic_entry(int apic, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector);
+extern void ioapic_write_entry(int apic, int pin,
+			       struct IO_APIC_route_entry e);
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index c745a306f7d..5f2efc5d992 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_IPI_H
 #define _ASM_X86_IPI_H
 
+#ifdef CONFIG_X86_LOCAL_APIC
+
 /*
  * Copyright 2004 James Cleverdon, IBM.
  * Subject to the GNU Public License, v.2
@@ -55,8 +57,8 @@ static inline void __xapic_wait_icr_idle(void)
 		cpu_relax();
 }
 
-static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
-				       unsigned int dest)
+static inline void
+__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
 {
 	/*
 	 * Subtle. In the case of the 'never do double writes' workaround
@@ -87,8 +89,8 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
  * This is used to send an IPI with no shorthand notation (the destination is
  * specified in bits 56 to 63 of the ICR).
  */
-static inline void __send_IPI_dest_field(unsigned int mask, int vector,
-					 unsigned int dest)
+static inline void
+ __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
 {
 	unsigned long cfg;
 
@@ -117,41 +119,46 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector,
 	native_apic_mem_write(APIC_ICR, cfg);
 }
 
-static inline void send_IPI_mask_sequence(const struct cpumask *mask,
-					  int vector)
-{
-	unsigned long flags;
-	unsigned long query_cpu;
+extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
+						 int vector);
+extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+							 int vector);
+#include <asm/genapic.h>
 
-	/*
-	 * Hack. The clustered APIC addressing mode doesn't allow us to send
-	 * to an arbitrary mask, so I do a unicast to each CPU instead.
-	 * - mbligh
-	 */
-	local_irq_save(flags);
-	for_each_cpu(query_cpu, mask) {
-		__send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
-				      vector, APIC_DEST_PHYSICAL);
-	}
-	local_irq_restore(flags);
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+							 int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+							 int vector);
+
+/* Avoid include hell */
+#define NMI_VECTOR 0x02
+
+extern int no_broadcast;
+
+static inline void __default_local_send_IPI_allbutself(int vector)
+{
+	if (no_broadcast || vector == NMI_VECTOR)
+		apic->send_IPI_mask_allbutself(cpu_online_mask, vector);
+	else
+		__default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, apic->dest_logical);
 }
 
-static inline void send_IPI_mask_allbutself(const struct cpumask *mask,
-					    int vector)
+static inline void __default_local_send_IPI_all(int vector)
 {
-	unsigned long flags;
-	unsigned int query_cpu;
-	unsigned int this_cpu = smp_processor_id();
-
-	/* See Hack comment above */
-
-	local_irq_save(flags);
-	for_each_cpu(query_cpu, mask)
-		if (query_cpu != this_cpu)
-			__send_IPI_dest_field(
-				per_cpu(x86_cpu_to_apicid, query_cpu),
-				vector, APIC_DEST_PHYSICAL);
-	local_irq_restore(flags);
+	if (no_broadcast || vector == NMI_VECTOR)
+		apic->send_IPI_mask(cpu_online_mask, vector);
+	else
+		__default_send_IPI_shortcut(APIC_DEST_ALLINC, vector, apic->dest_logical);
 }
 
+#ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_logical(const struct cpumask *mask,
+						 int vector);
+extern void default_send_IPI_allbutself(int vector);
+extern void default_send_IPI_all(int vector);
+extern void default_send_IPI_self(int vector);
+#endif
+
+#endif
+
 #endif /* _ASM_X86_IPI_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 592688ed04d..107eb219669 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -36,9 +36,11 @@ static inline int irq_canonicalize(int irq)
 extern void fixup_irqs(void);
 #endif
 
-extern unsigned int do_IRQ(struct pt_regs *regs);
 extern void init_IRQ(void);
 extern void native_init_IRQ(void);
+extern bool handle_irq(unsigned irq, struct pt_regs *regs);
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
 
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 89c898ab298..77843225b7e 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_X86_IRQ_REGS_H
+#define _ASM_X86_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+#define ARCH_HAS_OWN_IRQ_REGS
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+	return percpu_read(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = get_irq_regs();
+	percpu_write(irq_regs, new_regs);
+
+	return old_regs;
+}
+
+#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
deleted file mode 100644
index 86afd747345..00000000000
--- a/arch/x86/include/asm/irq_regs_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_32_H
-#define _ASM_X86_IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
-	return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
-	struct pt_regs *old_regs;
-
-	old_regs = get_irq_regs();
-	x86_write_percpu(irq_regs, new_regs);
-
-	return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h
deleted file mode 100644
index 3dd9c0b7027..00000000000
--- a/arch/x86/include/asm/irq_regs_64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff65032b9..b07278c55e9 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -1,47 +1,69 @@
 #ifndef _ASM_X86_IRQ_VECTORS_H
 #define _ASM_X86_IRQ_VECTORS_H
 
-#include <linux/threads.h>
+/*
+ * Linux IRQ vector layout.
+ *
+ * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can
+ * be defined by Linux. They are used as a jump table by the CPU when a
+ * given vector is triggered - by a CPU-external, CPU-internal or
+ * software-triggered event.
+ *
+ * Linux sets the kernel code address each entry jumps to early during
+ * bootup, and never changes them. This is the general layout of the
+ * IDT entries:
+ *
+ *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
+ *  Vectors  32 ... 127 : device interrupts
+ *  Vector  128         : legacy int80 syscall interface
+ *  Vectors 129 ... 237 : device interrupts
+ *  Vectors 238 ... 255 : special interrupts
+ *
+ * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
+ *
+ * This file enumerates the exact layout of them:
+ */
 
-#define NMI_VECTOR		0x02
+#define NMI_VECTOR			0x02
 
 /*
  * IDT vectors usable for external interrupt sources start
  * at 0x20:
  */
-#define FIRST_EXTERNAL_VECTOR	0x20
+#define FIRST_EXTERNAL_VECTOR		0x20
 
 #ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR		0x80
+# define SYSCALL_VECTOR			0x80
 #else
-# define IA32_SYSCALL_VECTOR	0x80
+# define IA32_SYSCALL_VECTOR		0x80
 #endif
 
 /*
  * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
  * cleanup after irq migration.
  */
-#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
+#define IRQ_MOVE_CLEANUP_VECTOR		FIRST_EXTERNAL_VECTOR
 
 /*
  * 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
@@ -49,119 +71,98 @@
  *  some of the following vectors are 'rare', they are merged
  *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
  *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
  */
-#ifdef CONFIG_X86_32
-
-# define SPURIOUS_APIC_VECTOR		0xff
-# define ERROR_APIC_VECTOR		0xfe
-# define INVALIDATE_TLB_VECTOR		0xfd
-# define RESCHEDULE_VECTOR		0xfc
-# define CALL_FUNCTION_VECTOR		0xfb
-# define CALL_FUNCTION_SINGLE_VECTOR	0xfa
-# define THERMAL_APIC_VECTOR		0xf0
-
-#else
 
 #define SPURIOUS_APIC_VECTOR		0xff
+/*
+ * Sanity check
+ */
+#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
+# error SPURIOUS_APIC_VECTOR definition error
+#endif
+
 #define ERROR_APIC_VECTOR		0xfe
 #define RESCHEDULE_VECTOR		0xfd
 #define CALL_FUNCTION_VECTOR		0xfc
 #define CALL_FUNCTION_SINGLE_VECTOR	0xfb
 #define THERMAL_APIC_VECTOR		0xfa
-#define THRESHOLD_APIC_VECTOR		0xf9
-#define UV_BAU_MESSAGE			0xf8
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS	8
 
+#ifdef CONFIG_X86_32
+/* 0xf8 - 0xf9 : free */
+#else
+# define THRESHOLD_APIC_VECTOR		0xf9
+# define UV_BAU_MESSAGE			0xf8
 #endif
 
+/* f0-f7 used for spreading out TLB flushes: */
+#define INVALIDATE_TLB_VECTOR_END	0xf7
+#define INVALIDATE_TLB_VECTOR_START	0xf0
+#define NUM_INVALIDATE_TLB_VECTORS	   8
+
 /*
  * Local APIC timer IRQ vector is on a different priority level,
  * to work around the 'lost local interrupt if more than 2 IRQ
  * sources per level' errata.
  */
-#define LOCAL_TIMER_VECTOR	0xef
+#define LOCAL_TIMER_VECTOR		0xef
+
+/*
+ * Performance monitoring interrupt vector:
+ */
+#define LOCAL_PERF_VECTOR		0xee
 
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
  * start at 0x31(0x41) to spread out vectors evenly between priority
  * levels. (0x80 is the syscall vector)
  */
-#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
-
-#define NR_VECTORS		256
+#define FIRST_DEVICE_VECTOR		(IRQ15_VECTOR + 2)
 
-#define FPU_IRQ			13
+#define NR_VECTORS			 256
 
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
+#define FPU_IRQ				  13
 
-#define NR_IRQS_LEGACY		16
+#define	FIRST_VM86_IRQ			   3
+#define LAST_VM86_IRQ			  15
 
-#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
-
-#ifndef CONFIG_SPARSE_IRQ
-# if NR_CPUS < MAX_IO_APICS
-#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
-#else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-#  define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+#ifndef __ASSEMBLY__
+static inline int invalid_vm86_irq(int irq)
+{
+	return irq < 3 || irq > 15;
+}
 #endif
 
-#elif defined(CONFIG_X86_VOYAGER)
-
-# define NR_IRQS		224
+/*
+ * Size the maximum number of interrupts.
+ *
+ * If the irq_desc[] array has a sparse layout, we can size things
+ * generously - it scales up linearly with the maximum number of CPUs,
+ * and the maximum number of IO-APICs, whichever is higher.
+ *
+ * In other cases we size more conservatively, to not create too large
+ * static arrays.
+ */
 
-#else /* IO_APIC || VOYAGER */
+#define NR_IRQS_LEGACY			  16
 
-# define NR_IRQS		16
+#define CPU_VECTOR_LIMIT		(  8 * NR_CPUS      )
+#define IO_APIC_VECTOR_LIMIT		( 32 * MAX_IO_APICS )
 
+#ifdef CONFIG_X86_IO_APIC
+# ifdef CONFIG_SPARSE_IRQ
+#  define NR_IRQS					\
+	(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?	\
+		(NR_VECTORS + CPU_VECTOR_LIMIT)  :	\
+		(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
+# else
+#  if NR_CPUS < MAX_IO_APICS
+#   define NR_IRQS 			(NR_VECTORS + 4*CPU_VECTOR_LIMIT)
+#  else
+#   define NR_IRQS			(NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#  endif
+# endif
+#else /* !CONFIG_X86_IO_APIC: */
+# define NR_IRQS			NR_IRQS_LEGACY
 #endif
 
-/* Voyager specific defines */
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0			0
-#define VIC_CPI_LEVEL1			1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI			2
-#define VIC_INVALIDATE_CPI		3
-#define VIC_RESCHEDULE_CPI		4
-#define VIC_ENABLE_IRQ_CPI		5
-#define VIC_CALL_FUNCTION_CPI		6
-#define VIC_CALL_FUNCTION_SINGLE_CPI	7
-
-/* Now the QIC CPIs:  Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET			1
-#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_SINGLE_CPI	(VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_SINGLE_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT			8
-#define VIC_CMN_INT			15
-
-/* This is the boot CPI for alternate processors.  It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
-
-
 #endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index c61d8b2ab8b..0ceb6d19ed3 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -9,23 +9,8 @@
 # define PAGES_NR		4
 #else
 # define PA_CONTROL_PAGE	0
-# define VA_CONTROL_PAGE	1
-# define PA_PGD			2
-# define VA_PGD			3
-# define PA_PUD_0		4
-# define VA_PUD_0		5
-# define PA_PMD_0		6
-# define VA_PMD_0		7
-# define PA_PTE_0		8
-# define VA_PTE_0		9
-# define PA_PUD_1		10
-# define VA_PUD_1		11
-# define PA_PMD_1		12
-# define VA_PMD_1		13
-# define PA_PTE_1		14
-# define VA_PTE_1		15
-# define PA_TABLE_PAGE		16
-# define PAGES_NR		17
+# define PA_TABLE_PAGE		1
+# define PAGES_NR		2
 #endif
 
 #ifdef CONFIG_X86_32
@@ -157,9 +142,9 @@ relocate_kernel(unsigned long indirection_page,
 		unsigned long start_address) ATTRIB_NORET;
 #endif
 
-#ifdef CONFIG_X86_32
 #define ARCH_HAS_KIMAGE_ARCH
 
+#ifdef CONFIG_X86_32
 struct kimage_arch {
 	pgd_t *pgd;
 #ifdef CONFIG_X86_PAE
@@ -169,6 +154,12 @@ struct kimage_arch {
 	pte_t *pte0;
 	pte_t *pte1;
 };
+#else
+struct kimage_arch {
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+};
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h
deleted file mode 100644
index cc09cbbee27..00000000000
--- a/arch/x86/include/asm/mach-default/mach_apic.h
+++ /dev/null
@@ -1,168 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_APIC_H
-#define _ASM_X86_MACH_DEFAULT_MACH_APIC_H
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-#include <mach_apicdef.h>
-#include <asm/smp.h>
-
-#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
-
-static inline const struct cpumask *target_cpus(void)
-{ 
-#ifdef CONFIG_SMP
-	return cpu_online_mask;
-#else
-	return cpumask_of(0);
-#endif
-} 
-
-#define NO_BALANCE_IRQ (0)
-#define esr_disable (0)
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#define TARGET_CPUS	  (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and)
-#define phys_pkg_id	(genapic->phys_pkg_id)
-#define vector_allocation_domain    (genapic->vector_allocation_domain)
-#define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
-#define send_IPI_self (genapic->send_IPI_self)
-#define wakeup_secondary_cpu (genapic->wakeup_cpu)
-extern void setup_apic_routing(void);
-#else
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-#define TARGET_CPUS (target_cpus())
-#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-	apic_write(APIC_LDR, val);
-}
-
-static inline int apic_id_registered(void)
-{
-	return physid_isset(read_apic_id(), phys_cpu_present_map);
-}
-
-static inline unsigned int cpu_mask_to_apicid(const struct cpumask *cpumask)
-{
-	return cpumask_bits(cpumask)[0];
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-						  const struct cpumask *andmask)
-{
-	unsigned long mask1 = cpumask_bits(cpumask)[0];
-	unsigned long mask2 = cpumask_bits(andmask)[0];
-	unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
-
-	return (unsigned int)(mask1 & mask2 & mask3);
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-static inline void setup_apic_routing(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-					"Flat", nr_ioapics);
-#endif
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-static inline void vector_allocation_domain(int cpu, struct cpumask *retmask)
-{
-        /* Careful. Some cpus do not strictly honor the set of cpus
-         * specified in the interrupt destination when using lowest
-         * priority interrupt delivery mode.
-         *
-         * In particular there was a hyperthreading cpu observed to
-         * deliver interrupts to the wrong hyperthread when only one
-         * hyperthread was specified in the interrupt desitination.
-         */
-	*retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
-}
-#endif
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return physid_isset(apicid, bitmap);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	return phys_map;
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	return 1 << cpu;
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
-		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	return physid_mask_of_physid(phys_apicid);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-#endif /* CONFIG_X86_LOCAL_APIC */
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_apicdef.h b/arch/x86/include/asm/mach-default/mach_apicdef.h
deleted file mode 100644
index 53179936d6c..00000000000
--- a/arch/x86/include/asm/mach-default/mach_apicdef.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H
-#define _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H
-
-#include <asm/apic.h>
-
-#ifdef CONFIG_X86_64
-#define	APIC_ID_MASK		(genapic->apic_id_mask)
-#define GET_APIC_ID(x)		(genapic->get_apic_id(x))
-#define	SET_APIC_ID(x)		(genapic->set_apic_id(x))
-#else
-#define		APIC_ID_MASK		(0xF<<24)
-static inline unsigned get_apic_id(unsigned long x) 
-{
-	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)
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-default/mach_ipi.h b/arch/x86/include/asm/mach-default/mach_ipi.h
deleted file mode 100644
index 191312d155d..00000000000
--- a/arch/x86/include/asm/mach-default/mach_ipi.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_IPI_H
-#define _ASM_X86_MACH_DEFAULT_MACH_IPI_H
-
-/* Avoid include hell */
-#define NMI_VECTOR 0x02
-
-void send_IPI_mask_bitmask(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-void __send_IPI_shortcut(unsigned int shortcut, int vector);
-
-extern int no_broadcast;
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define send_IPI_mask (genapic->send_IPI_mask)
-#define send_IPI_mask_allbutself (genapic->send_IPI_mask_allbutself)
-#else
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_bitmask(mask, vector);
-}
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-#endif
-
-static inline void __local_send_IPI_allbutself(int vector)
-{
-	if (no_broadcast || vector == NMI_VECTOR)
-		send_IPI_mask_allbutself(cpu_online_mask, vector);
-	else
-		__send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
-}
-
-static inline void __local_send_IPI_all(int vector)
-{
-	if (no_broadcast || vector == NMI_VECTOR)
-		send_IPI_mask(cpu_online_mask, vector);
-	else
-		__send_IPI_shortcut(APIC_DEST_ALLINC, vector);
-}
-
-#ifdef CONFIG_X86_64
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-#else
-static inline void send_IPI_allbutself(int vector)
-{
-	/*
-	 * if there are no other CPUs in the system then we get an APIC send 
-	 * error if we try to broadcast, thus avoid sending IPIs in this case.
-	 */
-	if (!(num_online_cpus() > 1))
-		return;
-
-	__local_send_IPI_allbutself(vector);
-	return;
-}
-
-static inline void send_IPI_all(int vector)
-{
-	__local_send_IPI_all(vector);
-}
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpparse.h b/arch/x86/include/asm/mach-default/mach_mpparse.h
deleted file mode 100644
index c70a263d68c..00000000000
--- a/arch/x86/include/asm/mach-default/mach_mpparse.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H
-#define _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H
-
-static inline int
-mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
-{
-	return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	return 0;
-}
-
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpspec.h b/arch/x86/include/asm/mach-default/mach_mpspec.h
deleted file mode 100644
index e85ede686be..00000000000
--- a/arch/x86/include/asm/mach-default/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H
-#define _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#if CONFIG_BASE_SMALL == 0
-#define MAX_MP_BUSSES 256
-#else
-#define MAX_MP_BUSSES 32
-#endif
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
deleted file mode 100644
index 89897a6a65b..00000000000
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ /dev/null
@@ -1,41 +0,0 @@
-#ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
-#define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW (0x467)
-#define TRAMPOLINE_PHYS_HIGH (0x469)
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-	while (!atomic_read(deassert))
-		cpu_relax();
-	return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-#ifdef CONFIG_SMP
-extern void __inquire_remote_apic(int apicid);
-#else /* CONFIG_SMP */
-static inline void __inquire_remote_apic(int apicid)
-{
-}
-#endif /* CONFIG_SMP */
-
-static inline void inquire_remote_apic(int apicid)
-{
-	if (apic_verbosity >= APIC_DEBUG)
-		__inquire_remote_apic(apicid);
-}
-
-#endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mach-generic/gpio.h b/arch/x86/include/asm/mach-generic/gpio.h
deleted file mode 100644
index 995c45efdb3..00000000000
--- a/arch/x86/include/asm/mach-generic/gpio.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_GPIO_H
-#define _ASM_X86_MACH_GENERIC_GPIO_H
-
-int gpio_request(unsigned gpio, const char *label);
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-int gpio_to_irq(unsigned gpio);
-int irq_to_gpio(unsigned irq);
-
-#include <asm-generic/gpio.h>           /* cansleep wrappers */
-
-#endif /* _ASM_X86_MACH_GENERIC_GPIO_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h
deleted file mode 100644
index 48553e958ad..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_apic.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_APIC_H
-#define _ASM_X86_MACH_GENERIC_MACH_APIC_H
-
-#include <asm/genapic.h>
-
-#define esr_disable (genapic->ESR_DISABLE)
-#define NO_BALANCE_IRQ (genapic->no_balance_irq)
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL (genapic->apic_destination_logical)
-#define TARGET_CPUS	  (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define ioapic_phys_id_map (genapic->ioapic_phys_id_map)
-#define setup_apic_routing (genapic->setup_apic_routing)
-#define multi_timer_check (genapic->multi_timer_check)
-#define apicid_to_node (genapic->apicid_to_node)
-#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) 
-#define cpu_present_to_apicid (genapic->cpu_present_to_apicid)
-#define apicid_to_cpu_present (genapic->apicid_to_cpu_present)
-#define setup_portio_remap (genapic->setup_portio_remap)
-#define check_apicid_present (genapic->check_apicid_present)
-#define check_phys_apicid_present (genapic->check_phys_apicid_present)
-#define check_apicid_used (genapic->check_apicid_used)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and)
-#define vector_allocation_domain (genapic->vector_allocation_domain)
-#define enable_apic_mode (genapic->enable_apic_mode)
-#define phys_pkg_id (genapic->phys_pkg_id)
-#define wakeup_secondary_cpu (genapic->wakeup_cpu)
-
-extern void generic_bigsmp_probe(void);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apicdef.h b/arch/x86/include/asm/mach-generic/mach_apicdef.h
deleted file mode 100644
index 68041f3802f..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_apicdef.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_APICDEF_H
-#define _ASM_X86_MACH_GENERIC_MACH_APICDEF_H
-
-#ifndef APIC_DEFINITION
-#include <asm/genapic.h>
-
-#define GET_APIC_ID (genapic->get_apic_id)
-#define APIC_ID_MASK (genapic->apic_id_mask)
-#endif
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_ipi.h b/arch/x86/include/asm/mach-generic/mach_ipi.h
deleted file mode 100644
index ffd637e3c3d..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_ipi.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_IPI_H
-#define _ASM_X86_MACH_GENERIC_MACH_IPI_H
-
-#include <asm/genapic.h>
-
-#define send_IPI_mask (genapic->send_IPI_mask)
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpparse.h b/arch/x86/include/asm/mach-generic/mach_mpparse.h
deleted file mode 100644
index 9444ab8dca9..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_mpparse.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H
-#define _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H
-
-
-extern int mps_oem_check(struct mpc_table *, char *, char *);
-
-extern int acpi_madt_oem_check(char *, char *);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpspec.h b/arch/x86/include/asm/mach-generic/mach_mpspec.h
deleted file mode 100644
index 3bc40722657..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H
-#define _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-/* Summit or generic (i.e. installer) kernels need lots of bus entries. */
-/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
-#define MAX_MP_BUSSES 260
-
-extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_wakecpu.h b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
deleted file mode 100644
index 1ab16b168c8..00000000000
--- a/arch/x86/include/asm/mach-generic/mach_wakecpu.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
-#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low)
-#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high)
-#define wait_for_init_deassert (genapic->wait_for_init_deassert)
-#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic)
-#define store_NMI_vector (genapic->store_NMI_vector)
-#define restore_NMI_vector (genapic->restore_NMI_vector)
-#define inquire_remote_apic (genapic->inquire_remote_apic)
-
-#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-rdc321x/gpio.h b/arch/x86/include/asm/mach-rdc321x/gpio.h
deleted file mode 100644
index c210ab5788b..00000000000
--- a/arch/x86/include/asm/mach-rdc321x/gpio.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _ASM_X86_MACH_RDC321X_GPIO_H
-#define _ASM_X86_MACH_RDC321X_GPIO_H
-
-#include <linux/kernel.h>
-
-extern int rdc_gpio_get_value(unsigned gpio);
-extern void rdc_gpio_set_value(unsigned gpio, int value);
-extern int rdc_gpio_direction_input(unsigned gpio);
-extern int rdc_gpio_direction_output(unsigned gpio, int value);
-extern int rdc_gpio_request(unsigned gpio, const char *label);
-extern void rdc_gpio_free(unsigned gpio);
-extern void __init rdc321x_gpio_setup(void);
-
-/* Wrappers for the arch-neutral GPIO API */
-
-static inline int gpio_request(unsigned gpio, const char *label)
-{
-	return rdc_gpio_request(gpio, label);
-}
-
-static inline void gpio_free(unsigned gpio)
-{
-	might_sleep();
-	rdc_gpio_free(gpio);
-}
-
-static inline int gpio_direction_input(unsigned gpio)
-{
-	return rdc_gpio_direction_input(gpio);
-}
-
-static inline int gpio_direction_output(unsigned gpio, int value)
-{
-	return rdc_gpio_direction_output(gpio, value);
-}
-
-static inline int gpio_get_value(unsigned gpio)
-{
-	return rdc_gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-	rdc_gpio_set_value(gpio, value);
-}
-
-static inline int gpio_to_irq(unsigned gpio)
-{
-	return gpio;
-}
-
-static inline int irq_to_gpio(unsigned irq)
-{
-	return irq;
-}
-
-/* For cansleep */
-#include <asm-generic/gpio.h>
-
-#endif /* _ASM_X86_MACH_RDC321X_GPIO_H */
diff --git a/arch/x86/include/asm/mach-default/mach_timer.h b/arch/x86/include/asm/mach_timer.h
index 853728519ae..853728519ae 100644
--- a/arch/x86/include/asm/mach-default/mach_timer.h
+++ b/arch/x86/include/asm/mach_timer.h
diff --git a/arch/x86/include/asm/mach-default/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f7920601e47..f7920601e47 100644
--- a/arch/x86/include/asm/mach-default/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
index 5a65b107ad5..031f6266f42 100644
--- a/arch/x86/include/asm/math_emu.h
+++ b/arch/x86/include/asm/math_emu.h
@@ -1,31 +1,18 @@
 #ifndef _ASM_X86_MATH_EMU_H
 #define _ASM_X86_MATH_EMU_H
 
+#include <asm/ptrace.h>
+#include <asm/vm86.h>
+
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
    automatically by the 80386/80486.
    */
-struct info {
+struct math_emu_info {
 	long ___orig_eip;
-	long ___ebx;
-	long ___ecx;
-	long ___edx;
-	long ___esi;
-	long ___edi;
-	long ___ebp;
-	long ___eax;
-	long ___ds;
-	long ___es;
-	long ___fs;
-	long ___orig_eax;
-	long ___eip;
-	long ___cs;
-	long ___eflags;
-	long ___esp;
-	long ___ss;
-	long ___vm86_es; /* This and the following only in vm86 mode */
-	long ___vm86_ds;
-	long ___vm86_fs;
-	long ___vm86_gs;
+	union {
+		struct pt_regs *regs;
+		struct kernel_vm86_regs *vm86;
+	};
 };
 #endif /* _ASM_X86_MATH_EMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 8aeeb3fd73d..f923203dc39 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -21,11 +21,54 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
-#ifdef CONFIG_X86_32
-# include "mmu_context_32.h"
-#else
-# include "mmu_context_64.h"
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
+#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+		/* stop flush ipis for the previous mm */
+		cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
+		cpu_set(cpu, next->cpu_vm_mask);
+
+		/* Re-load page tables */
+		load_cr3(next->pgd);
+
+		/*
+		 * load the LDT, if the LDT is different:
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_LDT_nolock(&next->context);
+	}
+#ifdef CONFIG_SMP
+	else {
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
+
+		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+			/* We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 */
+			load_cr3(next->pgd);
+			load_LDT_nolock(&next->context);
+		}
+	}
+#endif
+}
 
 #define activate_mm(prev, next)			\
 do {						\
@@ -33,5 +76,17 @@ do {						\
 	switch_mm((prev), (next), NULL);	\
 } while (0);
 
+#ifdef CONFIG_X86_32
+#define deactivate_mm(tsk, mm)			\
+do {						\
+	lazy_load_gs(0);			\
+} while (0)
+#else
+#define deactivate_mm(tsk, mm)			\
+do {						\
+	load_gs_index(0);			\
+	loadsegment(fs, 0);			\
+} while (0)
+#endif
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
deleted file mode 100644
index 7e98ce1d2c0..00000000000
--- a/arch/x86/include/asm/mmu_context_32.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_32_H
-#define _ASM_X86_MMU_CONTEXT_32_H
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev,
-			     struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	int cpu = smp_processor_id();
-
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		x86_write_percpu(cpu_tlbstate.active_mm, next);
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-
-		/* Re-load page tables */
-		load_cr3(next->pgd);
-
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
-
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload %cr3.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-	asm("movl %0,%%gs": :"r" (0));
-
-#endif /* _ASM_X86_MMU_CONTEXT_32_H */
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
deleted file mode 100644
index 677d36e9540..00000000000
--- a/arch/x86/include/asm/mmu_context_64.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_64_H
-#define _ASM_X86_MMU_CONTEXT_64_H
-
-#include <asm/pda.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	if (read_pda(mmu_state) == TLBSTATE_OK)
-		write_pda(mmu_state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		write_pda(mmu_state, TLBSTATE_OK);
-		write_pda(active_mm, next);
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-		load_cr3(next->pgd);
-
-		if (unlikely(next->context.ldt != prev->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		write_pda(mmu_state, TLBSTATE_OK);
-		if (read_pda(active_mm) != next)
-			BUG();
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-do {						\
-	load_gs_index(0);			\
-	asm volatile("movl %0,%%fs"::"r"(0));	\
-} while (0)
-
-#endif /* _ASM_X86_MMU_CONTEXT_64_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 62d14ce3cd0..5916c8df09d 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -9,7 +9,18 @@ extern int apic_version[MAX_APICS];
 extern int pic_mode;
 
 #ifdef CONFIG_X86_32
-#include <mach_mpspec.h>
+
+/*
+ * Summit or generic (i.e. installer) kernels need lots of bus entries.
+ * Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets.
+ */
+#if CONFIG_BASE_SMALL == 0
+# define MAX_MP_BUSSES		260
+#else
+# define MAX_MP_BUSSES		32
+#endif
+
+#define MAX_IRQ_SOURCES		256
 
 extern unsigned int def_to_bigsmp;
 extern u8 apicid_2_node[];
@@ -20,15 +31,15 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];
 extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 #endif
 
-#define MAX_APICID 256
+#define MAX_APICID		256
 
-#else
+#else /* CONFIG_X86_64: */
 
-#define MAX_MP_BUSSES 256
+#define MAX_MP_BUSSES		256
 /* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
-#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
+#define MAX_IRQ_SOURCES		(MAX_MP_BUSSES * 4)
 
-#endif
+#endif /* CONFIG_X86_64 */
 
 extern void early_find_smp_config(void);
 extern void early_get_smp_config(void);
@@ -45,11 +56,13 @@ extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
-extern void find_smp_config(void);
 extern void get_smp_config(void);
+
 #ifdef CONFIG_X86_MPPARSE
+extern void find_smp_config(void);
 extern void early_reserve_e820_mpc_new(void);
 #else
+static inline void find_smp_config(void) { }
 static inline void early_reserve_e820_mpc_new(void) { }
 #endif
 
@@ -60,9 +73,12 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+extern int acpi_probe_gsi(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
+extern int mp_find_ioapic(int gsi);
+extern int mp_find_ioapic_pin(int ioapic, int gsi);
 #else
 static inline int
 mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
@@ -71,6 +87,11 @@ mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 	return 0;
 }
 #endif
+#else /* !CONFIG_ACPI: */
+static inline int acpi_probe_gsi(void)
+{
+	return 0;
+}
 #endif /* CONFIG_ACPI */
 
 #define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
@@ -142,4 +163,10 @@ static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
 
 extern physid_mask_t phys_cpu_present_map;
 
+extern int generic_mps_oem_check(struct mpc_table *, char *, char *);
+
+extern int default_acpi_madt_oem_check(char *, char *);
+
+extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
+
 #endif /* _ASM_X86_MPSPEC_H */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 59568bc4767..4a7f96d7c18 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -24,17 +24,18 @@
 # endif
 #endif
 
-struct intel_mp_floating {
-	char mpf_signature[4];		/* "_MP_"			*/
-	unsigned int mpf_physptr;	/* Configuration table address	*/
-	unsigned char mpf_length;	/* Our length (paragraphs)	*/
-	unsigned char mpf_specification;/* Specification version	*/
-	unsigned char mpf_checksum;	/* Checksum (makes sum 0)	*/
-	unsigned char mpf_feature1;	/* Standard or configuration ?	*/
-	unsigned char mpf_feature2;	/* Bit7 set for IMCR|PIC	*/
-	unsigned char mpf_feature3;	/* Unused (0)			*/
-	unsigned char mpf_feature4;	/* Unused (0)			*/
-	unsigned char mpf_feature5;	/* Unused (0)			*/
+/* Intel MP Floating Pointer Structure */
+struct mpf_intel {
+	char signature[4];		/* "_MP_"			*/
+	unsigned int physptr;		/* Configuration table address	*/
+	unsigned char length;		/* Our length (paragraphs)	*/
+	unsigned char specification;	/* Specification version	*/
+	unsigned char checksum;		/* Checksum (makes sum 0)	*/
+	unsigned char feature1;		/* Standard or configuration ?	*/
+	unsigned char feature2;		/* Bit7 set for IMCR|PIC	*/
+	unsigned char feature3;		/* Unused (0)			*/
+	unsigned char feature4;		/* Unused (0)			*/
+	unsigned char feature5;		/* Unused (0)			*/
 };
 
 #define MPC_SIGNATURE "PCMP"
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
index 1e8bd30b4c1..9f0a5f5d29e 100644
--- a/arch/x86/include/asm/numaq.h
+++ b/arch/x86/include/asm/numaq.h
@@ -31,6 +31,8 @@
 extern int found_numaq;
 extern int get_memcfg_numaq(void);
 
+extern void *xquad_portio;
+
 /*
  * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
  */
diff --git a/arch/x86/include/asm/numaq/apic.h b/arch/x86/include/asm/numaq/apic.h
deleted file mode 100644
index bf37bc49bd8..00000000000
--- a/arch/x86/include/asm/numaq/apic.h
+++ /dev/null
@@ -1,142 +0,0 @@
-#ifndef __ASM_NUMAQ_APIC_H
-#define __ASM_NUMAQ_APIC_H
-
-#include <asm/io.h>
-#include <linux/mmzone.h>
-#include <linux/nodemask.h>
-
-#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
-
-static inline const cpumask_t *target_cpus(void)
-{
-	return &CPU_MASK_ALL;
-}
-
-#define NO_BALANCE_IRQ (1)
-#define esr_disable (1)
-
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
- 
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return physid_isset(apicid, bitmap);
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline int apic_id_registered(void)
-{
-	return 1;
-}
-
-static inline void init_apic_ldr(void)
-{
-	/* Already done in NUMA-Q firmware */
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-		"NUMA-Q", nr_ioapics);
-}
-
-/*
- * Skip adding the timer int on secondary nodes, which causes
- * a small but painful rift in the time-space continuum.
- */
-static inline int multi_timer_check(int apic, int irq)
-{
-	return apic != 0 && irq == 0;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* We don't have a good way to do this yet - hack */
-	return physids_promote(0xFUL);
-}
-
-/* Mapping from cpu number to logical apicid */
-extern u8 cpu_2_logical_apicid[];
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-}
-
-/*
- * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
- * cpu to APIC ID relation to properly interact with the intelligent
- * mode of the cluster controller.
- */
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < 60)
-		return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
-	else
-		return BAD_APICID;
-}
-
-static inline int apicid_to_node(int logical_apicid) 
-{
-	return logical_apicid >> 4;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
-{
-	int node = apicid_to_node(logical_apicid);
-	int cpu = __ffs(logical_apicid & 0xf);
-
-	return physid_mask_of_physid(cpu + 4*node);
-}
-
-extern void *xquad_portio;
-
-static inline void setup_portio_remap(void)
-{
-	int num_quads = num_online_nodes();
-
-	if (num_quads <= 1)
-       		return;
-
-	printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
-	xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
-	printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
-		(u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return (1);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-/*
- * We use physical apicids here, not logical, so just return the default
- * physical broadcast to stop people from breaking us
- */
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	return (int) 0xF;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-						  const struct cpumask *andmask)
-{
-	return (int) 0xF;
-}
-
-/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_NUMAQ_APIC_H */
diff --git a/arch/x86/include/asm/numaq/apicdef.h b/arch/x86/include/asm/numaq/apicdef.h
deleted file mode 100644
index e012a46cc22..00000000000
--- a/arch/x86/include/asm/numaq/apicdef.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_NUMAQ_APICDEF_H
-#define __ASM_NUMAQ_APICDEF_H
-
-
-#define APIC_ID_MASK (0xF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	        return (((x)>>24)&0x0F);
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/numaq/ipi.h b/arch/x86/include/asm/numaq/ipi.h
deleted file mode 100644
index a8374c65277..00000000000
--- a/arch/x86/include/asm/numaq/ipi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef __ASM_NUMAQ_IPI_H
-#define __ASM_NUMAQ_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_NUMAQ_IPI_H */
diff --git a/arch/x86/include/asm/numaq/mpparse.h b/arch/x86/include/asm/numaq/mpparse.h
deleted file mode 100644
index a2eeefcd1cc..00000000000
--- a/arch/x86/include/asm/numaq/mpparse.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_NUMAQ_MPPARSE_H
-#define __ASM_NUMAQ_MPPARSE_H
-
-extern void numaq_mps_oem_check(struct mpc_table *, char *, char *);
-
-#endif /* __ASM_NUMAQ_MPPARSE_H */
diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h
deleted file mode 100644
index 6f499df8edd..00000000000
--- a/arch/x86/include/asm/numaq/wakecpu.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef __ASM_NUMAQ_WAKECPU_H
-#define __ASM_NUMAQ_WAKECPU_H
-
-/* This file copes with machines that wakeup secondary CPUs by NMIs */
-
-#define TRAMPOLINE_PHYS_LOW (0x8)
-#define TRAMPOLINE_PHYS_HIGH (0xa)
-
-/* We don't do anything here because we use NMI's to boot instead */
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-}
-
-/*
- * Because we use NMIs rather than the INIT-STARTUP sequence to
- * bootstrap the CPUs, the APIC may be in a weird state. Kick it.
- */
-static inline void smp_callin_clear_local_apic(void)
-{
-	clear_local_APIC();
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-	printk("Storing NMI vector\n");
-	*high =
-	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH));
-	*low =
-	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW));
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-	printk("Restoring NMI vector\n");
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
-								 *high;
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
-								 *low;
-}
-
-static inline void inquire_remote_apic(int apicid)
-{
-}
-
-#endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 823cc931363..05f2da7f387 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -57,7 +57,6 @@ typedef struct { pgdval_t pgd; } pgd_t;
 typedef struct { pgprotval_t pgprot; } pgprot_t;
 
 extern int page_is_ram(unsigned long pagenr);
-extern int pagerange_is_ram(unsigned long start, unsigned long end);
 extern int devmem_is_allowed(unsigned long pagenr);
 extern void map_devmem(unsigned long pfn, unsigned long size,
 		       pgprot_t vma_prot);
@@ -163,7 +162,7 @@ static inline pteval_t native_pte_val(pte_t pte)
 	return pte.pte;
 }
 
-static inline pteval_t native_pte_flags(pte_t pte)
+static inline pteval_t pte_flags(pte_t pte)
 {
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
@@ -189,7 +188,6 @@ static inline pteval_t native_pte_flags(pte_t pte)
 #endif
 
 #define pte_val(x)	native_pte_val(x)
-#define pte_flags(x)	native_pte_flags(x)
 #define __pte(x)	native_make_pte(x)
 
 #endif	/* CONFIG_PARAVIRT */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5ebca29f44f..e27fdbe5f9e 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -13,8 +13,8 @@
 #define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
 #define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
 
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+#define IRQ_STACK_ORDER 2
+#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
 #define STACKFAULT_STACK 1
 #define DOUBLEFAULT_STACK 2
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ba3e2ff6aed..b788dfd2048 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -12,21 +12,38 @@
 #define CLBR_EAX  (1 << 0)
 #define CLBR_ECX  (1 << 1)
 #define CLBR_EDX  (1 << 2)
+#define CLBR_EDI  (1 << 3)
 
-#ifdef CONFIG_X86_64
-#define CLBR_RSI  (1 << 3)
-#define CLBR_RDI  (1 << 4)
+#ifdef CONFIG_X86_32
+/* CLBR_ANY should match all regs platform has. For i386, that's just it */
+#define CLBR_ANY  ((1 << 4) - 1)
+
+#define CLBR_ARG_REGS	(CLBR_EAX | CLBR_EDX | CLBR_ECX)
+#define CLBR_RET_REG	(CLBR_EAX | CLBR_EDX)
+#define CLBR_SCRATCH	(0)
+#else
+#define CLBR_RAX  CLBR_EAX
+#define CLBR_RCX  CLBR_ECX
+#define CLBR_RDX  CLBR_EDX
+#define CLBR_RDI  CLBR_EDI
+#define CLBR_RSI  (1 << 4)
 #define CLBR_R8   (1 << 5)
 #define CLBR_R9   (1 << 6)
 #define CLBR_R10  (1 << 7)
 #define CLBR_R11  (1 << 8)
+
 #define CLBR_ANY  ((1 << 9) - 1)
+
+#define CLBR_ARG_REGS	(CLBR_RDI | CLBR_RSI | CLBR_RDX | \
+			 CLBR_RCX | CLBR_R8 | CLBR_R9)
+#define CLBR_RET_REG	(CLBR_RAX)
+#define CLBR_SCRATCH	(CLBR_R10 | CLBR_R11)
+
 #include <asm/desc_defs.h>
-#else
-/* CLBR_ANY should match all regs platform has. For i386, that's just it */
-#define CLBR_ANY  ((1 << 3) - 1)
 #endif /* X86_64 */
 
+#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
+
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 #include <linux/cpumask.h>
@@ -40,6 +57,14 @@ struct tss_struct;
 struct mm_struct;
 struct desc_struct;
 
+/*
+ * Wrapper type for pointers to code which uses the non-standard
+ * calling convention.  See PV_CALL_SAVE_REGS_THUNK below.
+ */
+struct paravirt_callee_save {
+	void *func;
+};
+
 /* general info */
 struct pv_info {
 	unsigned int kernel_rpl;
@@ -189,11 +214,15 @@ struct pv_irq_ops {
 	 * expected to use X86_EFLAGS_IF; all other bits
 	 * returned from save_fl are undefined, and may be ignored by
 	 * restore_fl.
+	 *
+	 * NOTE: These functions callers expect the callee to preserve
+	 * more registers than the standard C calling convention.
 	 */
-	unsigned long (*save_fl)(void);
-	void (*restore_fl)(unsigned long);
-	void (*irq_disable)(void);
-	void (*irq_enable)(void);
+	struct paravirt_callee_save save_fl;
+	struct paravirt_callee_save restore_fl;
+	struct paravirt_callee_save irq_disable;
+	struct paravirt_callee_save irq_enable;
+
 	void (*safe_halt)(void);
 	void (*halt)(void);
 
@@ -244,7 +273,8 @@ struct pv_mmu_ops {
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
 	void (*flush_tlb_single)(unsigned long addr);
-	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+	void (*flush_tlb_others)(const struct cpumask *cpus,
+				 struct mm_struct *mm,
 				 unsigned long va);
 
 	/* Hooks for allocating and freeing a pagetable top-level */
@@ -278,12 +308,11 @@ struct pv_mmu_ops {
 	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep, pte_t pte);
 
-	pteval_t (*pte_val)(pte_t);
-	pteval_t (*pte_flags)(pte_t);
-	pte_t (*make_pte)(pteval_t pte);
+	struct paravirt_callee_save pte_val;
+	struct paravirt_callee_save make_pte;
 
-	pgdval_t (*pgd_val)(pgd_t);
-	pgd_t (*make_pgd)(pgdval_t pgd);
+	struct paravirt_callee_save pgd_val;
+	struct paravirt_callee_save make_pgd;
 
 #if PAGETABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
@@ -298,12 +327,12 @@ struct pv_mmu_ops {
 
 	void (*set_pud)(pud_t *pudp, pud_t pudval);
 
-	pmdval_t (*pmd_val)(pmd_t);
-	pmd_t (*make_pmd)(pmdval_t pmd);
+	struct paravirt_callee_save pmd_val;
+	struct paravirt_callee_save make_pmd;
 
 #if PAGETABLE_LEVELS == 4
-	pudval_t (*pud_val)(pud_t);
-	pud_t (*make_pud)(pudval_t pud);
+	struct paravirt_callee_save pud_val;
+	struct paravirt_callee_save make_pud;
 
 	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
 #endif	/* PAGETABLE_LEVELS == 4 */
@@ -388,6 +417,8 @@ extern struct pv_lock_ops pv_lock_ops;
 	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
 
 unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
 unsigned paravirt_patch_ignore(unsigned len);
 unsigned paravirt_patch_call(void *insnbuf,
 			     const void *target, u16 tgt_clobbers,
@@ -479,25 +510,45 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS			unsigned long __eax, __edx, __ecx
+#define PVOP_VCALL_ARGS				\
+	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
 #define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
+
+#define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x)		"d" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x)		"c" ((unsigned long)(x))
+
 #define PVOP_VCALL_CLOBBERS		"=a" (__eax), "=d" (__edx),	\
 					"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS		PVOP_VCALL_CLOBBERS
+
+#define PVOP_VCALLEE_CLOBBERS		"=a" (__eax), "=d" (__edx)
+#define PVOP_CALLEE_CLOBBERS		PVOP_VCALLEE_CLOBBERS
+
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
-#else
-#define PVOP_VCALL_ARGS		unsigned long __edi, __esi, __edx, __ecx
+#else  /* CONFIG_X86_64 */
+#define PVOP_VCALL_ARGS					\
+	unsigned long __edi = __edi, __esi = __esi,	\
+		__edx = __edx, __ecx = __ecx
 #define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
+
+#define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x)		"d" ((unsigned long)(x))
+#define PVOP_CALL_ARG4(x)		"c" ((unsigned long)(x))
+
 #define PVOP_VCALL_CLOBBERS	"=D" (__edi),				\
 				"=S" (__esi), "=d" (__edx),		\
 				"=c" (__ecx)
-
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+#define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
+#define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
+
 #define EXTRA_CLOBBERS	 , "r8", "r9", "r10", "r11"
 #define VEXTRA_CLOBBERS	 , "rax", "r8", "r9", "r10", "r11"
-#endif
+#endif	/* CONFIG_X86_32 */
 
 #ifdef CONFIG_PARAVIRT_DEBUG
 #define PVOP_TEST_NULL(op)	BUG_ON(op == NULL)
@@ -505,10 +556,11 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)	((void)op)
 #endif
 
-#define __PVOP_CALL(rettype, op, pre, post, ...)			\
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,		\
+		      pre, post, ...)					\
 	({								\
 		rettype __ret;						\
-		PVOP_CALL_ARGS;					\
+		PVOP_CALL_ARGS;						\
 		PVOP_TEST_NULL(op);					\
 		/* This is 32-bit specific, but is okay in 64-bit */	\
 		/* since this condition will never hold */		\
@@ -516,70 +568,113 @@ int paravirt_disable_iospace(void);
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : PVOP_CALL_CLOBBERS		\
+				     : call_clbr			\
 				     : paravirt_type(op),		\
-				       paravirt_clobber(CLBR_ANY),	\
+				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
-				     : "memory", "cc" EXTRA_CLOBBERS);	\
+				     : "memory", "cc" extra_clbr);	\
 			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
 		} else {						\
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : PVOP_CALL_CLOBBERS		\
+				     : call_clbr			\
 				     : paravirt_type(op),		\
-				       paravirt_clobber(CLBR_ANY),	\
+				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
-				     : "memory", "cc" EXTRA_CLOBBERS);	\
+				     : "memory", "cc" extra_clbr);	\
 			__ret = (rettype)__eax;				\
 		}							\
 		__ret;							\
 	})
-#define __PVOP_VCALL(op, pre, post, ...)				\
+
+#define __PVOP_CALL(rettype, op, pre, post, ...)			\
+	____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS,	\
+		      EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...)			\
+	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+		      PVOP_CALLEE_CLOBBERS, ,				\
+		      pre, post, ##__VA_ARGS__)
+
+
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...)	\
 	({								\
 		PVOP_VCALL_ARGS;					\
 		PVOP_TEST_NULL(op);					\
 		asm volatile(pre					\
 			     paravirt_alt(PARAVIRT_CALL)		\
 			     post					\
-			     : PVOP_VCALL_CLOBBERS			\
+			     : call_clbr				\
 			     : paravirt_type(op),			\
-			       paravirt_clobber(CLBR_ANY),		\
+			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
-			     : "memory", "cc" VEXTRA_CLOBBERS);		\
+			     : "memory", "cc" extra_clbr);		\
 	})
 
+#define __PVOP_VCALL(op, pre, post, ...)				\
+	____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS,		\
+		       VEXTRA_CLOBBERS,					\
+		       pre, post, ##__VA_ARGS__)
+
+#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)			\
+	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+		      PVOP_VCALLEE_CLOBBERS, ,				\
+		      pre, post, ##__VA_ARGS__)
+
+
+
 #define PVOP_CALL0(rettype, op)						\
 	__PVOP_CALL(rettype, op, "", "")
 #define PVOP_VCALL0(op)							\
 	__PVOP_VCALL(op, "", "")
 
+#define PVOP_CALLEE0(rettype, op)					\
+	__PVOP_CALLEESAVE(rettype, op, "", "")
+#define PVOP_VCALLEE0(op)						\
+	__PVOP_VCALLEESAVE(op, "", "")
+
+
 #define PVOP_CALL1(rettype, op, arg1)					\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)))
+	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
 #define PVOP_VCALL1(op, arg1)						\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)))
+	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+
+#define PVOP_CALLEE1(rettype, op, arg1)					\
+	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+#define PVOP_VCALLEE1(op, arg1)						\
+	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+
 
 #define PVOP_CALL2(rettype, op, arg1, arg2)				\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), 	\
-	"1" ((unsigned long)(arg2)))
+	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
+		    PVOP_CALL_ARG2(arg2))
 #define PVOP_VCALL2(op, arg1, arg2)					\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), 		\
-	"1" ((unsigned long)(arg2)))
+	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
+		     PVOP_CALL_ARG2(arg2))
+
+#define PVOP_CALLEE2(rettype, op, arg1, arg2)				\
+	__PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1),	\
+			  PVOP_CALL_ARG2(arg2))
+#define PVOP_VCALLEE2(op, arg1, arg2)					\
+	__PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1),		\
+			   PVOP_CALL_ARG2(arg2))
+
 
 #define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+	__PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1),		\
+		    PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 #define PVOP_VCALL3(op, arg1, arg2, arg3)				\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+	__PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1),			\
+		     PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
 
 /* This is the only difference in x86_64. We can make it much simpler */
 #ifdef CONFIG_X86_32
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
 	__PVOP_CALL(rettype, op,					\
 		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
+		    PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
 	__PVOP_VCALL(op,						\
 		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
@@ -587,13 +682,13 @@ int paravirt_disable_iospace(void);
 		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
 #else
 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
-	"3"((unsigned long)(arg4)))
+	__PVOP_CALL(rettype, op, "", "",				\
+		    PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),		\
+		    PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
-	"3"((unsigned long)(arg4)))
+	__PVOP_VCALL(op, "", "",					\
+		     PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
+		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 #endif
 
 static inline int paravirt_enabled(void)
@@ -984,10 +1079,11 @@ static inline void __flush_tlb_single(unsigned long addr)
 	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
 }
 
-static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+				    struct mm_struct *mm,
 				    unsigned long va)
 {
-	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
+	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
 }
 
 static inline int paravirt_pgd_alloc(struct mm_struct *mm)
@@ -1059,13 +1155,13 @@ static inline pte_t __pte(pteval_t val)
 	pteval_t ret;
 
 	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val, (u64)val >> 32);
+		ret = PVOP_CALLEE2(pteval_t,
+				   pv_mmu_ops.make_pte,
+				   val, (u64)val >> 32);
 	else
-		ret = PVOP_CALL1(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val);
+		ret = PVOP_CALLEE1(pteval_t,
+				   pv_mmu_ops.make_pte,
+				   val);
 
 	return (pte_t) { .pte = ret };
 }
@@ -1075,29 +1171,12 @@ static inline pteval_t pte_val(pte_t pte)
 	pteval_t ret;
 
 	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte);
-
-	return ret;
-}
-
-static inline pteval_t pte_flags(pte_t pte)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte, (u64)pte.pte >> 32);
+		ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
+				   pte.pte, (u64)pte.pte >> 32);
 	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte);
+		ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
+				   pte.pte);
 
-#ifdef CONFIG_PARAVIRT_DEBUG
-	BUG_ON(ret & PTE_PFN_MASK);
-#endif
 	return ret;
 }
 
@@ -1106,11 +1185,11 @@ static inline pgd_t __pgd(pgdval_t val)
 	pgdval_t ret;
 
 	if (sizeof(pgdval_t) > sizeof(long))
-		ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
-				 val, (u64)val >> 32);
+		ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
+				   val, (u64)val >> 32);
 	else
-		ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
-				 val);
+		ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
+				   val);
 
 	return (pgd_t) { ret };
 }
@@ -1120,11 +1199,11 @@ static inline pgdval_t pgd_val(pgd_t pgd)
 	pgdval_t ret;
 
 	if (sizeof(pgdval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd, (u64)pgd.pgd >> 32);
+		ret =  PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
+				    pgd.pgd, (u64)pgd.pgd >> 32);
 	else
-		ret =  PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd);
+		ret =  PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
+				    pgd.pgd);
 
 	return ret;
 }
@@ -1188,11 +1267,11 @@ static inline pmd_t __pmd(pmdval_t val)
 	pmdval_t ret;
 
 	if (sizeof(pmdval_t) > sizeof(long))
-		ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd,
-				 val, (u64)val >> 32);
+		ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
+				   val, (u64)val >> 32);
 	else
-		ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd,
-				 val);
+		ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
+				   val);
 
 	return (pmd_t) { ret };
 }
@@ -1202,11 +1281,11 @@ static inline pmdval_t pmd_val(pmd_t pmd)
 	pmdval_t ret;
 
 	if (sizeof(pmdval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val,
-				  pmd.pmd, (u64)pmd.pmd >> 32);
+		ret =  PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
+				    pmd.pmd, (u64)pmd.pmd >> 32);
 	else
-		ret =  PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val,
-				  pmd.pmd);
+		ret =  PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
+				    pmd.pmd);
 
 	return ret;
 }
@@ -1228,11 +1307,11 @@ static inline pud_t __pud(pudval_t val)
 	pudval_t ret;
 
 	if (sizeof(pudval_t) > sizeof(long))
-		ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud,
-				 val, (u64)val >> 32);
+		ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
+				   val, (u64)val >> 32);
 	else
-		ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud,
-				 val);
+		ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
+				   val);
 
 	return (pud_t) { ret };
 }
@@ -1242,11 +1321,11 @@ static inline pudval_t pud_val(pud_t pud)
 	pudval_t ret;
 
 	if (sizeof(pudval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val,
-				  pud.pud, (u64)pud.pud >> 32);
+		ret =  PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
+				    pud.pud, (u64)pud.pud >> 32);
 	else
-		ret =  PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val,
-				  pud.pud);
+		ret =  PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
+				    pud.pud);
 
 	return ret;
 }
@@ -1352,14 +1431,7 @@ static inline void arch_leave_lazy_cpu_mode(void)
 	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
 }
 
-static inline void arch_flush_lazy_cpu_mode(void)
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-}
-
+void arch_flush_lazy_cpu_mode(void);
 
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
@@ -1372,13 +1444,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-static inline void arch_flush_lazy_mmu_mode(void)
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-}
+void arch_flush_lazy_mmu_mode(void);
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				unsigned long phys, pgprot_t flags)
@@ -1387,9 +1453,10 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 }
 
 void _paravirt_nop(void);
-#define paravirt_nop	((void *)_paravirt_nop)
+u32 _paravirt_ident_32(u32);
+u64 _paravirt_ident_64(u64);
 
-void paravirt_use_bytelocks(void);
+#define paravirt_nop	((void *)_paravirt_nop)
 
 #ifdef CONFIG_SMP
 
@@ -1402,6 +1469,7 @@ static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
 {
@@ -1438,12 +1506,37 @@ extern struct paravirt_patch_site __parainstructions[],
 	__parainstructions_end[];
 
 #ifdef CONFIG_X86_32
-#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;"
-#define PV_RESTORE_REGS "popl %%edx; popl %%ecx"
+#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
+#define PV_RESTORE_REGS "popl %edx; popl %ecx;"
+
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS		"pushl %ecx;"
+#define PV_RESTORE_ALL_CALLER_REGS	"popl  %ecx;"
+
 #define PV_FLAGS_ARG "0"
 #define PV_EXTRA_CLOBBERS
 #define PV_VEXTRA_CLOBBERS
 #else
+/* save and restore all caller-save registers, except return value */
+#define PV_SAVE_ALL_CALLER_REGS						\
+	"push %rcx;"							\
+	"push %rdx;"							\
+	"push %rsi;"							\
+	"push %rdi;"							\
+	"push %r8;"							\
+	"push %r9;"							\
+	"push %r10;"							\
+	"push %r11;"
+#define PV_RESTORE_ALL_CALLER_REGS					\
+	"pop %r11;"							\
+	"pop %r10;"							\
+	"pop %r9;"							\
+	"pop %r8;"							\
+	"pop %rdi;"							\
+	"pop %rsi;"							\
+	"pop %rdx;"							\
+	"pop %rcx;"
+
 /* We save some registers, but all of them, that's too much. We clobber all
  * caller saved registers but the argument parameter */
 #define PV_SAVE_REGS "pushq %%rdi;"
@@ -1453,52 +1546,76 @@ extern struct paravirt_patch_site __parainstructions[],
 #define PV_FLAGS_ARG "D"
 #endif
 
+/*
+ * Generate a thunk around a function which saves all caller-save
+ * registers except for the return value.  This allows C functions to
+ * be called from assembler code where fewer than normal registers are
+ * available.  It may also help code generation around calls from C
+ * code if the common case doesn't use many registers.
+ *
+ * When a callee is wrapped in a thunk, the caller can assume that all
+ * arg regs and all scratch registers are preserved across the
+ * call. The return value in rax/eax will not be saved, even for void
+ * functions.
+ */
+#define PV_CALLEE_SAVE_REGS_THUNK(func)					\
+	extern typeof(func) __raw_callee_save_##func;			\
+	static void *__##func##__ __used = func;			\
+									\
+	asm(".pushsection .text;"					\
+	    "__raw_callee_save_" #func ": "				\
+	    PV_SAVE_ALL_CALLER_REGS					\
+	    "call " #func ";"						\
+	    PV_RESTORE_ALL_CALLER_REGS					\
+	    "ret;"							\
+	    ".popsection")
+
+/* Get a reference to a callee-save function */
+#define PV_CALLEE_SAVE(func)						\
+	((struct paravirt_callee_save) { __raw_callee_save_##func })
+
+/* Promise that "func" already uses the right calling convention */
+#define __PV_IS_CALLEE_SAVE(func)			\
+	((struct paravirt_callee_save) { func })
+
 static inline unsigned long __raw_local_save_flags(void)
 {
 	unsigned long f;
 
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
+	asm volatile(paravirt_alt(PARAVIRT_CALL)
 		     : "=a"(f)
 		     : paravirt_type(pv_irq_ops.save_fl),
 		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc" PV_VEXTRA_CLOBBERS);
+		     : "memory", "cc");
 	return f;
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
+	asm volatile(paravirt_alt(PARAVIRT_CALL)
 		     : "=a"(f)
 		     : PV_FLAGS_ARG(f),
 		       paravirt_type(pv_irq_ops.restore_fl),
 		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc" PV_EXTRA_CLOBBERS);
+		     : "memory", "cc");
 }
 
 static inline void raw_local_irq_disable(void)
 {
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
+	asm volatile(paravirt_alt(PARAVIRT_CALL)
 		     :
 		     : paravirt_type(pv_irq_ops.irq_disable),
 		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+		     : "memory", "eax", "cc");
 }
 
 static inline void raw_local_irq_enable(void)
 {
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
+	asm volatile(paravirt_alt(PARAVIRT_CALL)
 		     :
 		     : paravirt_type(pv_irq_ops.irq_enable),
 		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+		     : "memory", "eax", "cc");
 }
 
 static inline unsigned long __raw_local_irq_save(void)
@@ -1541,33 +1658,49 @@ static inline unsigned long __raw_local_irq_save(void)
 	.popsection
 
 
+#define COND_PUSH(set, mask, reg)			\
+	.if ((~(set)) & mask); push %reg; .endif
+#define COND_POP(set, mask, reg)			\
+	.if ((~(set)) & mask); pop %reg; .endif
+
 #ifdef CONFIG_X86_64
-#define PV_SAVE_REGS				\
-	push %rax;				\
-	push %rcx;				\
-	push %rdx;				\
-	push %rsi;				\
-	push %rdi;				\
-	push %r8;				\
-	push %r9;				\
-	push %r10;				\
-	push %r11
-#define PV_RESTORE_REGS				\
-	pop %r11;				\
-	pop %r10;				\
-	pop %r9;				\
-	pop %r8;				\
-	pop %rdi;				\
-	pop %rsi;				\
-	pop %rdx;				\
-	pop %rcx;				\
-	pop %rax
+
+#define PV_SAVE_REGS(set)			\
+	COND_PUSH(set, CLBR_RAX, rax);		\
+	COND_PUSH(set, CLBR_RCX, rcx);		\
+	COND_PUSH(set, CLBR_RDX, rdx);		\
+	COND_PUSH(set, CLBR_RSI, rsi);		\
+	COND_PUSH(set, CLBR_RDI, rdi);		\
+	COND_PUSH(set, CLBR_R8, r8);		\
+	COND_PUSH(set, CLBR_R9, r9);		\
+	COND_PUSH(set, CLBR_R10, r10);		\
+	COND_PUSH(set, CLBR_R11, r11)
+#define PV_RESTORE_REGS(set)			\
+	COND_POP(set, CLBR_R11, r11);		\
+	COND_POP(set, CLBR_R10, r10);		\
+	COND_POP(set, CLBR_R9, r9);		\
+	COND_POP(set, CLBR_R8, r8);		\
+	COND_POP(set, CLBR_RDI, rdi);		\
+	COND_POP(set, CLBR_RSI, rsi);		\
+	COND_POP(set, CLBR_RDX, rdx);		\
+	COND_POP(set, CLBR_RCX, rcx);		\
+	COND_POP(set, CLBR_RAX, rax)
+
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
 #else
-#define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
-#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
+#define PV_SAVE_REGS(set)			\
+	COND_PUSH(set, CLBR_EAX, eax);		\
+	COND_PUSH(set, CLBR_EDI, edi);		\
+	COND_PUSH(set, CLBR_ECX, ecx);		\
+	COND_PUSH(set, CLBR_EDX, edx)
+#define PV_RESTORE_REGS(set)			\
+	COND_POP(set, CLBR_EDX, edx);		\
+	COND_POP(set, CLBR_ECX, ecx);		\
+	COND_POP(set, CLBR_EDI, edi);		\
+	COND_POP(set, CLBR_EAX, eax)
+
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
 #define PARA_INDIRECT(addr)	*%cs:addr
@@ -1579,15 +1712,15 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #define DISABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
-		  PV_SAVE_REGS;						\
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
-		  PV_RESTORE_REGS;)			\
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define ENABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
-		  PV_SAVE_REGS;						\
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
-		  PV_RESTORE_REGS;)
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define USERGS_SYSRET32							\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
@@ -1617,11 +1750,15 @@ static inline unsigned long __raw_local_irq_save(void)
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
 		  swapgs)
 
+/*
+ * Note: swapgs is very special, and in practise is either going to be
+ * implemented with a single "swapgs" instruction or something very
+ * special.  Either way, we don't need to save any registers for
+ * it.
+ */
 #define SWAPGS								\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  PV_SAVE_REGS;						\
-		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
-		  PV_RESTORE_REGS					\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
 		 )
 
 #define GET_CR2_INTO_RCX				\
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index b8493b3b989..9709fdff661 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,10 +5,8 @@
 
 #ifdef CONFIG_X86_PAT
 extern int pat_enabled;
-extern void validate_pat_support(struct cpuinfo_x86 *c);
 #else
 static const int pat_enabled;
-static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
 #endif
 
 extern void pat_init(void);
@@ -17,6 +15,4 @@ extern int reserve_memtype(u64 start, u64 end,
 		unsigned long req_type, unsigned long *ret_type);
 extern int free_memtype(u64 start, u64 end);
 
-extern void pat_disable(char *reason);
-
 #endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/mach-default/pci-functions.h b/arch/x86/include/asm/pci-functions.h
index ed0bab42735..ed0bab42735 100644
--- a/arch/x86/include/asm/mach-default/pci-functions.h
+++ b/arch/x86/include/asm/pci-functions.h
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
deleted file mode 100644
index 2fbfff88df3..00000000000
--- a/arch/x86/include/asm/pda.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef _ASM_X86_PDA_H
-#define _ASM_X86_PDA_H
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <asm/page.h>
-
-/* Per processor datastructure. %gs points to it while the kernel runs */
-struct x8664_pda {
-	struct task_struct *pcurrent;	/* 0  Current process */
-	unsigned long data_offset;	/* 8 Per cpu data offset from linker
-					   address */
-	unsigned long kernelstack;	/* 16 top of kernel stack for current */
-	unsigned long oldrsp;		/* 24 user rsp for system call */
-	int irqcount;			/* 32 Irq nesting counter. Starts -1 */
-	unsigned int cpunumber;		/* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
-	unsigned long stack_canary;	/* 40 stack canary value */
-					/* gcc-ABI: this canary MUST be at
-					   offset 40!!! */
-#endif
-	char *irqstackptr;
-	short nodenumber;		/* number of current node (32k max) */
-	short in_bootmem;		/* pda lives in bootmem */
-	unsigned int __softirq_pending;
-	unsigned int __nmi_count;	/* number of NMI on this CPUs */
-	short mmu_state;
-	short isidle;
-	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;
-extern void pda_init(int);
-
-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val)					\
-do {									\
-	typedef typeof(_proxy_pda.field) T__;				\
-	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */	\
-	switch (sizeof(_proxy_pda.field)) {				\
-	case 2:								\
-		asm(op "w %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	case 4:								\
-		asm(op "l %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i" (pda_offset(field)));				\
-		break;							\
-	case 8:								\
-		asm(op "q %1,%%gs:%c2":					\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	default:							\
-		__bad_pda_field();					\
-	}								\
-} while (0)
-
-#define pda_from_op(op, field)			\
-({						\
-	typeof(_proxy_pda.field) ret__;		\
-	switch (sizeof(_proxy_pda.field)) {	\
-	case 2:					\
-		asm(op "w %%gs:%c1,%0" :	\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 4:					\
-		asm(op "l %%gs:%c1,%0":		\
-		    "=r" (ret__):		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 8:					\
-		asm(op "q %%gs:%c1,%0":		\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	default:				\
-		__bad_pda_field();		\
-	}					\
-	ret__;					\
-})
-
-#define read_pda(field)		pda_from_op("mov", field)
-#define write_pda(field, val)	pda_to_op("mov", field, val)
-#define add_pda(field, val)	pda_to_op("add", field, val)
-#define sub_pda(field, val)	pda_to_op("sub", field, val)
-#define or_pda(field, val)	pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define test_and_clear_bit_pda(bit, field)				\
-({									\
-	int old__;							\
-	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"			\
-		     : "=r" (old__), "+m" (_proxy_pda.field)		\
-		     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
-	old__;								\
-})
-
-#endif
-
-#define PDA_STACKOFFSET (5*8)
-
-#endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ece72053ba6..aee103b26d0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -2,53 +2,12 @@
 #define _ASM_X86_PERCPU_H
 
 #ifdef CONFIG_X86_64
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
-   in the PDA. Longer term the PDA and every per cpu variable
-   should be just put into a single section and referenced directly
-   from %gs */
-
-#ifdef CONFIG_SMP
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
+#define __percpu_seg		gs
+#define __percpu_mov_op		movq
+#else
+#define __percpu_seg		fs
+#define __percpu_mov_op		movl
 #endif
-#include <asm-generic/percpu.h>
-
-DECLARE_PER_CPU(struct x8664_pda, pda);
-
-/*
- * These are supposed to be implemented as a single instruction which
- * operates on the per-cpu data base segment.  x86-64 doesn't have
- * that yet, so this is a fairly inefficient workaround for the
- * meantime.  The single instruction is atomic with respect to
- * preemption and interrupts, so we need to explicitly disable
- * interrupts here to achieve the same effect.  However, because it
- * can be used from within interrupt-disable/enable, we can't actually
- * disable interrupts; disabling preemption is enough.
- */
-#define x86_read_percpu(var)						\
-	({								\
-		typeof(per_cpu_var(var)) __tmp;				\
-		preempt_disable();					\
-		__tmp = __get_cpu_var(var);				\
-		preempt_enable();					\
-		__tmp;							\
-	})
-
-#define x86_write_percpu(var, val)					\
-	do {								\
-		preempt_disable();					\
-		__get_cpu_var(var) = (val);				\
-		preempt_enable();					\
-	} while(0)
-
-#else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
 
@@ -65,47 +24,48 @@ DECLARE_PER_CPU(struct x8664_pda, pda);
  *    PER_CPU(cpu_gdt_descr, %ebx)
  */
 #ifdef CONFIG_SMP
-#define PER_CPU(var, reg)				\
-	movl %fs:per_cpu__##this_cpu_off, reg;		\
+#define PER_CPU(var, reg)						\
+	__percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg;	\
 	lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)	%fs:per_cpu__##var
+#define PER_CPU_VAR(var)	%__percpu_seg:per_cpu__##var
 #else /* ! SMP */
-#define PER_CPU(var, reg)			\
-	movl $per_cpu__##var, reg
+#define PER_CPU(var, reg)						\
+	__percpu_mov_op $per_cpu__##var, reg
 #define PER_CPU_VAR(var)	per_cpu__##var
 #endif	/* SMP */
 
+#ifdef CONFIG_X86_64_SMP
+#define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
+#else
+#define INIT_PER_CPU_VAR(var)  per_cpu__##var
+#endif
+
 #else /* ...!ASSEMBLY */
 
+#include <linux/stringify.h>
+
+#ifdef CONFIG_SMP
+#define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
+#define __my_cpu_offset		percpu_read(this_cpu_off)
+#else
+#define __percpu_arg(x)		"%" #x
+#endif
+
 /*
- * PER_CPU finds an address of a per-cpu variable.
+ * Initialized pointers to per-cpu variables needed for the boot
+ * processor need to use these macros to get the proper address
+ * offset from __per_cpu_load on SMP.
  *
- * Args:
- *    var - variable name
- *    cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
+ * There also must be an entry in vmlinux_64.lds.S
  */
-#ifdef CONFIG_SMP
-
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
-
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-
-#else  /* !SMP */
-
-#define __percpu_seg ""
-
-#endif	/* SMP */
-
-#include <asm-generic/percpu.h>
+#define DECLARE_INIT_PER_CPU(var) \
+       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
 
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+#ifdef CONFIG_X86_64_SMP
+#define init_per_cpu_var(var)  init_per_cpu__##var
+#else
+#define init_per_cpu_var(var)  per_cpu_var(var)
+#endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
@@ -120,20 +80,25 @@ do {							\
 	}						\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b %1,"__percpu_seg"%0"		\
+		asm(op "b %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
 	case 2:						\
-		asm(op "w %1,"__percpu_seg"%0"		\
+		asm(op "w %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
 	case 4:						\
-		asm(op "l %1,"__percpu_seg"%0"		\
+		asm(op "l %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
+	case 8:						\
+		asm(op "q %1,"__percpu_arg(0)		\
+		    : "+m" (var)			\
+		    : "re" ((T__)val));			\
+		break;					\
 	default: __bad_percpu_size();			\
 	}						\
 } while (0)
@@ -143,17 +108,22 @@ do {							\
 	typeof(var) ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_seg"%1,%0"		\
+		asm(op "b "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_seg"%1,%0"		\
+		asm(op "w "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_seg"%1,%0"		\
+		asm(op "l "__percpu_arg(1)",%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
+	case 8:						\
+		asm(op "q "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
@@ -162,13 +132,30 @@ do {							\
 	ret__;						\
 })
 
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var)	percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val)	percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val)	percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val)	percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val)	percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define x86_test_and_clear_bit_percpu(bit, var)				\
+({									\
+	int old__;							\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
+		     : "=r" (old__), "+m" (per_cpu__##var)		\
+		     : "dIr" (bit));					\
+	old__;								\
+})
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
 #endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
 
 #ifdef CONFIG_SMP
 
@@ -195,9 +182,9 @@ do {							\
 #define	early_per_cpu_ptr(_name) (_name##_early_ptr)
 #define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
 #define	early_per_cpu(_name, _cpu) 				\
-	(early_per_cpu_ptr(_name) ?				\
-		early_per_cpu_ptr(_name)[_cpu] :		\
-		per_cpu(_name, _cpu))
+	*(early_per_cpu_ptr(_name) ?				\
+		&early_per_cpu_ptr(_name)[_cpu] :		\
+		&per_cpu(_name, _cpu))
 
 #else	/* !CONFIG_SMP */
 #define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 178205305ac..8fef0f6bfbb 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -242,78 +242,106 @@ static inline int pmd_large(pmd_t pte)
 		(_PAGE_PSE | _PAGE_PRESENT);
 }
 
+static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
+{
+	pteval_t v = native_pte_val(pte);
+
+	return native_make_pte(v | set);
+}
+
+static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
+{
+	pteval_t v = native_pte_val(pte);
+
+	return native_make_pte(v & ~clear);
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+	return pte_clear_flags(pte, _PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+	return pte_clear_flags(pte, _PAGE_ACCESSED);
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_RW);
+	return pte_clear_flags(pte, _PAGE_RW);
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_NX);
+	return pte_clear_flags(pte, _PAGE_NX);
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_DIRTY);
+	return pte_set_flags(pte, _PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+	return pte_set_flags(pte, _PAGE_ACCESSED);
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_RW);
+	return pte_set_flags(pte, _PAGE_RW);
 }
 
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_PSE);
+	return pte_set_flags(pte, _PAGE_PSE);
 }
 
 static inline pte_t pte_clrhuge(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_PSE);
+	return pte_clear_flags(pte, _PAGE_PSE);
 }
 
 static inline pte_t pte_mkglobal(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_GLOBAL);
+	return pte_set_flags(pte, _PAGE_GLOBAL);
 }
 
 static inline pte_t pte_clrglobal(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
+	return pte_clear_flags(pte, _PAGE_GLOBAL);
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+	return pte_set_flags(pte, _PAGE_SPECIAL);
 }
 
 extern pteval_t __supported_pte_mask;
 
+/*
+ * Mask out unsupported bits in a present pgprot.  Non-present pgprots
+ * can use those bits for other purposes, so leave them be.
+ */
+static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
+{
+	pgprotval_t protval = pgprot_val(pgprot);
+
+	if (protval & _PAGE_PRESENT)
+		protval &= __supported_pte_mask;
+
+	return protval;
+}
+
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
+	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
+		     massage_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
+	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
+		     massage_pgprot(pgprot));
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
@@ -325,7 +353,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 * the newprot (if present):
 	 */
 	val &= _PAGE_CHG_MASK;
-	val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
+	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
 
 	return __pte(val);
 }
@@ -341,7 +369,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
 
-#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
+#define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
 static inline int is_new_memtype_allowed(unsigned long flags,
 						unsigned long new_flags)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 100ac483a0b..1c4e247c51f 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -11,7 +11,6 @@
 #include <asm/processor.h>
 #include <linux/bitops.h>
 #include <linux/threads.h>
-#include <asm/pda.h>
 
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
index a8894647dd9..3ac5032fae0 100644
--- a/arch/x86/include/asm/prctl.h
+++ b/arch/x86/include/asm/prctl.h
@@ -6,8 +6,4 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
-#ifdef CONFIG_X86_64
-extern long sys_arch_prctl(int, unsigned long);
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 091cd8855f2..a0133838b67 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -73,7 +73,7 @@ struct cpuinfo_x86 {
 	char			pad0;
 #else
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
-	int			 x86_tlbsize;
+	int			x86_tlbsize;
 	__u8			x86_virt_bits;
 	__u8			x86_phys_bits;
 #endif
@@ -353,7 +353,7 @@ struct i387_soft_struct {
 	u8			no_update;
 	u8			rm;
 	u8			alimit;
-	struct info		*info;
+	struct math_emu_info	*info;
 	u32			entry_eip;
 };
 
@@ -378,7 +378,29 @@ union thread_xstate {
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+union irq_stack_union {
+	char irq_stack[IRQ_STACK_SIZE];
+	/*
+	 * GCC hardcodes the stack canary as %gs:40.  Since the
+	 * irq_stack is the object at %gs:0, we reserve the bottom
+	 * 48 bytes of the irq stack for the canary.
+	 */
+	struct {
+		char gs_base[40];
+		unsigned long stack_canary;
+	};
+};
+
+DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_INIT_PER_CPU(irq_stack_union);
+
+DECLARE_PER_CPU(char *, irq_stack_ptr);
+#else	/* X86_64 */
+#ifdef CONFIG_CC_STACKPROTECTOR
+DECLARE_PER_CPU(unsigned long, stack_canary);
 #endif
+#endif	/* X86_64 */
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
 extern unsigned int xstate_size;
@@ -752,9 +774,9 @@ extern int sysenter_setup(void);
 extern struct desc_ptr		early_gdt_descr;
 
 extern void cpu_set_gdt(int);
-extern void switch_to_new_gdt(void);
+extern void switch_to_new_gdt(int);
+extern void load_percpu_segment(int);
 extern void cpu_init(void);
-extern void init_gdt(int cpu);
 
 static inline unsigned long get_debugctlmsr(void)
 {
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index d6a22f92ba7..49fb3ecf3bb 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -18,11 +18,7 @@ extern void syscall32_cpu_init(void);
 
 extern void check_efer(void);
 
-#ifdef CONFIG_X86_BIOS_REBOOT
 extern int reboot_force;
-#else
-static const int reboot_force = 0;
-#endif
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6d34d954c22..e304b66abee 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -28,7 +28,7 @@ struct pt_regs {
 	int  xds;
 	int  xes;
 	int  xfs;
-	/* int  gs; */
+	int  xgs;
 	long orig_eax;
 	long eip;
 	int  xcs;
@@ -50,7 +50,7 @@ struct pt_regs {
 	unsigned long ds;
 	unsigned long es;
 	unsigned long fs;
-	/* int  gs; */
+	unsigned long gs;
 	unsigned long orig_ax;
 	unsigned long ip;
 	unsigned long cs;
diff --git a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h
index c8e9c8bed3d..c8e9c8bed3d 100644
--- a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h
+++ b/arch/x86/include/asm/rdc321x_defs.h
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 1dc1b51ac62..14e0ed86a6f 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -61,7 +61,7 @@
  *
  *  26 - ESPFIX small SS
  *  27 - per-cpu			[ offset to per-cpu data area ]
- *  28 - unused
+ *  28 - stack_canary-20		[ for stack protector ]
  *  29 - unused
  *  30 - unused
  *  31 - TSS for double fault handler
@@ -95,6 +95,13 @@
 #define __KERNEL_PERCPU 0
 #endif
 
+#define GDT_ENTRY_STACK_CANARY		(GDT_ENTRY_KERNEL_BASE + 16)
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY * 8)
+#else
+#define __KERNEL_STACK_CANARY		0
+#endif
+
 #define GDT_ENTRY_DOUBLEFAULT_TSS	31
 
 /*
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858cdc8a..45b40278b58 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_SETUP_H
 #define _ASM_X86_SETUP_H
 
+#ifdef __KERNEL__
+
 #define COMMAND_LINE_SIZE 2048
 
 #ifndef __ASSEMBLY__
@@ -8,10 +10,8 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
-
 void setup_bios_corruption_check(void);
 
-
 #ifdef CONFIG_X86_VISWS
 extern void visws_early_detect(void);
 extern int is_visws_box(void);
@@ -43,7 +43,7 @@ struct x86_quirks {
 	void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
 	void (*mpc_oem_pci_bus)(struct mpc_bus *m);
 	void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable,
-                                    unsigned short oemsize);
+				unsigned short oemsize);
 	int (*setup_ioapic_ids)(void);
 	int (*update_genapic)(void);
 };
@@ -56,8 +56,6 @@ extern unsigned long saved_video_mode;
 #endif
 #endif /* __ASSEMBLY__ */
 
-#ifdef __KERNEL__
-
 #ifdef __i386__
 
 #include <linux/pfn.h>
@@ -100,7 +98,6 @@ extern unsigned long init_pg_tables_start;
 extern unsigned long init_pg_tables_end;
 
 #else
-void __init x86_64_init_pda(void);
 void __init x86_64_start_kernel(char *real_mode);
 void __init x86_64_start_reservations(char *real_mode_data);
 
diff --git a/arch/x86/include/asm/mach-default/setup_arch.h b/arch/x86/include/asm/setup_arch.h
index 38846208b54..38846208b54 100644
--- a/arch/x86/include/asm/mach-default/setup_arch.h
+++ b/arch/x86/include/asm/setup_arch.h
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19953df61c5..47d0e21f2b9 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -15,34 +15,8 @@
 #  include <asm/io_apic.h>
 # endif
 #endif
-#include <asm/pda.h>
 #include <asm/thread_info.h>
-
-#ifdef CONFIG_X86_64
-
-extern cpumask_var_t cpu_callin_mask;
-extern cpumask_var_t cpu_callout_mask;
-extern cpumask_var_t cpu_initialized_mask;
-extern cpumask_var_t cpu_sibling_setup_mask;
-
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
-
-#endif /* CONFIG_X86_32 */
-
-extern void (*mtrr_hook)(void);
-extern void zap_low_mappings(void);
-
-extern int __cpuinit get_local_pda(int cpu);
+#include <asm/cpumask.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
@@ -50,9 +24,7 @@ extern unsigned int num_processors;
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-#ifdef CONFIG_X86_32
 DECLARE_PER_CPU(int, cpu_number);
-#endif
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
@@ -167,8 +139,6 @@ void play_dead_common(void);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-extern void prefill_possible_map(void);
-
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 
@@ -177,10 +147,6 @@ static inline int num_booting_cpus(void)
 {
 	return cpumask_weight(cpu_callout_mask);
 }
-#else
-static inline void prefill_possible_map(void)
-{
-}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus __cpuinitdata;
@@ -191,11 +157,11 @@ extern unsigned disabled_cpus __cpuinitdata;
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 extern int safe_smp_processor_id(void);
 
 #elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id()	read_pda(cpunumber)
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 
 #define stack_smp_processor_id()					\
 ({								\
@@ -205,10 +171,6 @@ extern int safe_smp_processor_id(void);
 })
 #define safe_smp_processor_id()		smp_processor_id()
 
-#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
-#define cpu_physical_id(cpu)		boot_cpu_physical_apicid
-#define safe_smp_processor_id()		0
-#define stack_smp_processor_id() 	0
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -220,28 +182,9 @@ static inline int logical_smp_processor_id(void)
 	return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
 }
 
-#include <mach_apicdef.h>
-static inline unsigned int read_apic_id(void)
-{
-	unsigned int reg;
-
-	reg = *(u32 *)(APIC_BASE + APIC_ID);
-
-	return GET_APIC_ID(reg);
-}
 #endif
 
-
-# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
 extern int hard_smp_processor_id(void);
-# else
-#include <mach_apicdef.h>
-static inline int hard_smp_processor_id(void)
-{
-	/* we don't want to mark this access volatile - bad code generation */
-	return read_apic_id();
-}
-# endif /* APIC_DEFINITION */
 
 #else /* CONFIG_X86_LOCAL_APIC */
 
@@ -251,11 +194,5 @@ static inline int hard_smp_processor_id(void)
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
-extern unsigned char boot_cpu_id;
-#else
-#define boot_cpu_id	0
-#endif
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 23bf52103b8..1def6011490 100644
--- a/arch/x86/include/asm/mach-default/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -13,10 +13,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	CMOS_WRITE(0xa, 0xf);
 	local_flush_tlb();
 	pr_debug("1.\n");
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+	*((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_high)) =
 								 start_eip >> 4;
 	pr_debug("2.\n");
-	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+	*((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_low)) =
 							 start_eip & 0xf;
 	pr_debug("3.\n");
 }
@@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	 */
 	CMOS_WRITE(0, 0xf);
 
-	*((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
+	*((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0;
 }
 
 static inline void __init smpboot_setup_io_apic(void)
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index d17c91981da..3a569665668 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -172,70 +172,8 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
 }
 
-#ifdef CONFIG_PARAVIRT
-/*
- * Define virtualization-friendly old-style lock byte lock, for use in
- * pv_lock_ops if desired.
- *
- * This differs from the pre-2.6.24 spinlock by always using xchgb
- * rather than decb to take the lock; this allows it to use a
- * zero-initialized lock structure.  It also maintains a 1-byte
- * contention counter, so that we can implement
- * __byte_spin_is_contended.
- */
-struct __byte_spinlock {
-	s8 lock;
-	s8 spinners;
-};
-
-static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	return bl->lock != 0;
-}
-
-static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	return bl->spinners != 0;
-}
-
-static inline void __byte_spin_lock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	s8 val = 1;
-
-	asm("1: xchgb %1, %0\n"
-	    "   test %1,%1\n"
-	    "   jz 3f\n"
-	    "   " LOCK_PREFIX "incb %2\n"
-	    "2: rep;nop\n"
-	    "   cmpb $1, %0\n"
-	    "   je 2b\n"
-	    "   " LOCK_PREFIX "decb %2\n"
-	    "   jmp 1b\n"
-	    "3:"
-	    : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
-}
-
-static inline int __byte_spin_trylock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	u8 old = 1;
-
-	asm("xchgb %1,%0"
-	    : "+m" (bl->lock), "+q" (old) : : "memory");
+#ifndef CONFIG_PARAVIRT
 
-	return old == 0;
-}
-
-static inline void __byte_spin_unlock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	smp_wmb();
-	bl->lock = 0;
-}
-#else  /* !CONFIG_PARAVIRT */
 static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
 {
 	return __ticket_spin_is_locked(lock);
@@ -245,6 +183,7 @@ static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
 {
 	return __ticket_spin_is_contended(lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
@@ -267,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
 	__raw_spin_lock(lock);
 }
 
-#endif	/* CONFIG_PARAVIRT */
+#endif
 
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
@@ -329,8 +268,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
 {
 	atomic_t *count = (atomic_t *)lock;
 
-	atomic_dec(count);
-	if (atomic_read(count) >= 0)
+	if (atomic_dec_return(count) >= 0)
 		return 1;
 	atomic_inc(count);
 	return 0;
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
new file mode 100644
index 00000000000..c2d742c6e15
--- /dev/null
+++ b/arch/x86/include/asm/stackprotector.h
@@ -0,0 +1,124 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and unfortunately gcc requires it to be at a fixed offset from %gs.
+ * On x86_64, the offset is 40 bytes and on x86_32 20 bytes.  x86_64
+ * and x86_32 use segment registers differently and thus handles this
+ * requirement differently.
+ *
+ * On x86_64, %gs is shared by percpu area and stack canary.  All
+ * percpu symbols are zero based and %gs points to the base of percpu
+ * area.  The first occupant of the percpu area is always
+ * irq_stack_union which contains stack_canary at offset 40.  Userland
+ * %gs is always saved and restored on kernel entry and exit using
+ * swapgs, so stack protector doesn't add any complexity there.
+ *
+ * On x86_32, it's slightly more complicated.  As in x86_64, %gs is
+ * used for userland TLS.  Unfortunately, some processors are much
+ * slower at loading segment registers with different value when
+ * entering and leaving the kernel, so the kernel uses %fs for percpu
+ * area and manages %gs lazily so that %gs is switched only when
+ * necessary, usually during task switch.
+ *
+ * As gcc requires the stack canary at %gs:20, %gs can't be managed
+ * lazily if stack protector is enabled, so the kernel saves and
+ * restores userland %gs on kernel entry and exit.  This behavior is
+ * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
+ * system.h to hide the details.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+
+#include <asm/tsc.h>
+#include <asm/processor.h>
+#include <asm/percpu.h>
+#include <asm/system.h>
+#include <asm/desc.h>
+#include <linux/random.h>
+
+/*
+ * 24 byte read-only segment initializer for stack canary.  Linker
+ * can't handle the address bit shifting.  Address will be set in
+ * head_32 for boot CPU and setup_per_cpu_areas() for others.
+ */
+#define GDT_STACK_CANARY_INIT						\
+	[GDT_ENTRY_STACK_CANARY] = { { { 0x00000018, 0x00409000 } } },
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	u64 canary;
+	u64 tsc;
+
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+#endif
+	/*
+	 * We both use the random pool and the current TSC as a source
+	 * of randomness. The TSC only matters for very early init,
+	 * there it already has some randomness on most systems. Later
+	 * on during the bootup the random pool has true entropy too.
+	 */
+	get_random_bytes(&canary, sizeof(canary));
+	tsc = __native_read_tsc();
+	canary += tsc + (tsc << 32UL);
+
+	current->stack_canary = canary;
+#ifdef CONFIG_X86_64
+	percpu_write(irq_stack_union.stack_canary, canary);
+#else
+	percpu_write(stack_canary, canary);
+#endif
+}
+
+static inline void setup_stack_canary_segment(int cpu)
+{
+#ifdef CONFIG_X86_32
+	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20;
+	struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
+	struct desc_struct desc;
+
+	desc = gdt_table[GDT_ENTRY_STACK_CANARY];
+	desc.base0 = canary & 0xffff;
+	desc.base1 = (canary >> 16) & 0xff;
+	desc.base2 = (canary >> 24) & 0xff;
+	write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
+#endif
+}
+
+static inline void load_stack_canary_segment(void)
+{
+#ifdef CONFIG_X86_32
+	asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+#endif
+}
+
+#else	/* CC_STACKPROTECTOR */
+
+#define GDT_STACK_CANARY_INIT
+
+/* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
+
+static inline void setup_stack_canary_segment(int cpu)
+{ }
+
+static inline void load_stack_canary_segment(void)
+{
+#ifdef CONFIG_X86_32
+	asm volatile ("mov %0, %%gs" : : "r" (0));
+#endif
+}
+
+#endif	/* CC_STACKPROTECTOR */
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h
deleted file mode 100644
index 93d2c8667cf..00000000000
--- a/arch/x86/include/asm/summit/apic.h
+++ /dev/null
@@ -1,202 +0,0 @@
-#ifndef __ASM_SUMMIT_APIC_H
-#define __ASM_SUMMIT_APIC_H
-
-#include <asm/smp.h>
-#include <linux/gfp.h>
-
-#define esr_disable (1)
-#define NO_BALANCE_IRQ (0)
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
-#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
-
-static inline const cpumask_t *target_cpus(void)
-{
-	/* CPU_MASK_ALL (0xff) has undefined behaviour with
-	 * dest_LowestPrio mode logical clustered apic interrupt routing
-	 * Just start on cpu 0.  IRQ balancing will spread load
-	 */
-	return &cpumask_of_cpu(0);
-}
-
-#define INT_DELIVERY_MODE (dest_LowestPrio)
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return 0;
-}
-
-/* we don't use the phys_cpu_present_map to indicate apicid presence */
-static inline unsigned long check_apicid_present(int bit)
-{
-	return 1;
-}
-
-#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
-
-extern u8 cpu_2_logical_apicid[];
-
-static inline void init_apic_ldr(void)
-{
-	unsigned long val, id;
-	int count = 0;
-	u8 my_id = (u8)hard_smp_processor_id();
-	u8 my_cluster = (u8)apicid_cluster(my_id);
-#ifdef CONFIG_SMP
-	u8 lid;
-	int i;
-
-	/* Create logical APIC IDs by counting CPUs already in cluster. */
-	for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
-		lid = cpu_2_logical_apicid[i];
-		if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
-			++count;
-	}
-#endif
-	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
-	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
-	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
-	id = my_cluster | (1UL << count);
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	val |= SET_APIC_LOGICAL_ID(id);
-	apic_write(APIC_LDR, val);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-static inline int apic_id_registered(void)
-{
-	return 1;
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  Summit.  Using %d I/O APICs\n",
-						nr_ioapics);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < nr_cpu_ids)
-		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0x0F);
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int apicid)
-{
-	return physid_mask_of_physid(0);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return 1;
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpus_weight(*cpumask);
-	/* Return id to all */
-	if (num_bits_set >= nr_cpu_ids)
-		return (int) 0xFF;
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = first_cpu(*cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpu_isset(cpu, *cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return 0xFF;
-			}
-			apicid = apicid | new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
-						  const struct cpumask *andmask)
-{
-	int apicid = cpu_to_logical_apicid(0);
-	cpumask_var_t cpumask;
-
-	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-		return apicid;
-
-	cpumask_and(cpumask, inmask, andmask);
-	cpumask_and(cpumask, cpumask, cpu_online_mask);
-	apicid = cpu_mask_to_apicid(cpumask);
-
-	free_cpumask_var(cpumask);
-	return apicid;
-}
-
-/* cpuid returns the value latched in the HW at reset, not the APIC ID
- * register's value.  For any box whose BIOS changes APIC IDs, like
- * clustered APIC systems, we must use hard_smp_processor_id.
- *
- * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
- */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return hard_smp_processor_id() >> index_msb;
-}
-
-#endif /* __ASM_SUMMIT_APIC_H */
diff --git a/arch/x86/include/asm/summit/apicdef.h b/arch/x86/include/asm/summit/apicdef.h
deleted file mode 100644
index f3fbca1f61c..00000000000
--- a/arch/x86/include/asm/summit/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_SUMMIT_APICDEF_H
-#define __ASM_SUMMIT_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (x>>24)&0xFF;
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/arch/x86/include/asm/summit/ipi.h b/arch/x86/include/asm/summit/ipi.h
deleted file mode 100644
index a8a2c24f50c..00000000000
--- a/arch/x86/include/asm/summit/ipi.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __ASM_SUMMIT_IPI_H
-#define __ASM_SUMMIT_IPI_H
-
-void send_IPI_mask_sequence(const cpumask_t *mask, int vector);
-void send_IPI_mask_allbutself(const cpumask_t *mask, int vector);
-
-static inline void send_IPI_mask(const cpumask_t *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		send_IPI_mask(&mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(&cpu_online_map, vector);
-}
-
-#endif /* __ASM_SUMMIT_IPI_H */
diff --git a/arch/x86/include/asm/summit/mpparse.h b/arch/x86/include/asm/summit/mpparse.h
deleted file mode 100644
index 380e86c0236..00000000000
--- a/arch/x86/include/asm/summit/mpparse.h
+++ /dev/null
@@ -1,109 +0,0 @@
-#ifndef __ASM_SUMMIT_MPPARSE_H
-#define __ASM_SUMMIT_MPPARSE_H
-
-#include <asm/tsc.h>
-
-extern int use_cyclone;
-
-#ifdef CONFIG_X86_SUMMIT_NUMA
-extern void setup_summit(void);
-#else
-#define setup_summit()	{}
-#endif
-
-static inline int mps_oem_check(struct mpc_table *mpc, char *oem,
-		char *productid)
-{
-	if (!strncmp(oem, "IBM ENSW", 8) &&
-			(!strncmp(productid, "VIGIL SMP", 9)
-			 || !strncmp(productid, "EXA", 3)
-			 || !strncmp(productid, "RUTHLESS SMP", 12))){
-		mark_tsc_unstable("Summit based system");
-		use_cyclone = 1; /*enable cyclone-timer*/
-		setup_summit();
-		return 1;
-	}
-	return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	if (!strncmp(oem_id, "IBM", 3) &&
-	    (!strncmp(oem_table_id, "SERVIGIL", 8)
-	     || !strncmp(oem_table_id, "EXA", 3))){
-		mark_tsc_unstable("Summit based system");
-		use_cyclone = 1; /*enable cyclone-timer*/
-		setup_summit();
-		return 1;
-	}
-	return 0;
-}
-
-struct rio_table_hdr {
-	unsigned char version;      /* Version number of this data structure           */
-	                            /* Version 3 adds chassis_num & WP_index           */
-	unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil)   */
-	unsigned char num_rio_dev;  /* # of RIO I/O devices (Cyclones and Winnipegs)   */
-} __attribute__((packed));
-
-struct scal_detail {
-	unsigned char node_id;      /* Scalability Node ID                             */
-	unsigned long CBAR;         /* Address of 1MB register space                   */
-	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port1node;    /* Node ID port connected to: 0xFF = None          */
-	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port2node;    /* Node ID port connected to: 0xFF = None          */
-	unsigned char port2port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char chassis_num;  /* 1 based Chassis number (1 = boot node)          */
-} __attribute__((packed));
-
-struct rio_detail {
-	unsigned char node_id;      /* RIO Node ID                                     */
-	unsigned long BBAR;         /* Address of 1MB register space                   */
-	unsigned char type;         /* Type of device                                  */
-	unsigned char owner_id;     /* For WPEG: Node ID of Cyclone that owns this WPEG*/
-	                            /* For CYC:  Node ID of Twister that owns this CYC */
-	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port1node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char first_slot;   /* For WPEG: Lowest slot number below this WPEG    */
-	                            /* For CYC:  0                                     */
-	unsigned char status;       /* For WPEG: Bit 0 = 1 : the XAPIC is used         */
-	                            /*                 = 0 : the XAPIC is not used, ie:*/
-	                            /*                     ints fwded to another XAPIC */
-	                            /*           Bits1:7 Reserved                      */
-	                            /* For CYC:  Bits0:7 Reserved                      */
-	unsigned char WP_index;     /* For WPEG: WPEG instance index - lower ones have */
-	                            /*           lower slot numbers/PCI bus numbers    */
-	                            /* For CYC:  No meaning                            */
-	unsigned char chassis_num;  /* 1 based Chassis number                          */
-	                            /* For LookOut WPEGs this field indicates the      */
-	                            /* Expansion Chassis #, enumerated from Boot       */
-	                            /* Node WPEG external port, then Boot Node CYC     */
-	                            /* external port, then Next Vigil chassis WPEG     */
-	                            /* external port, etc.                             */
-	                            /* Shared Lookouts have only 1 chassis number (the */
-	                            /* first one assigned)                             */
-} __attribute__((packed));
-
-
-typedef enum {
-	CompatTwister = 0,  /* Compatibility Twister               */
-	AltTwister    = 1,  /* Alternate Twister of internal 8-way */
-	CompatCyclone = 2,  /* Compatibility Cyclone               */
-	AltCyclone    = 3,  /* Alternate Cyclone of internal 8-way */
-	CompatWPEG    = 4,  /* Compatibility WPEG                  */
-	AltWPEG       = 5,  /* Second Planar WPEG                  */
-	LookOutAWPEG  = 6,  /* LookOut WPEG                        */
-	LookOutBWPEG  = 7,  /* LookOut WPEG                        */
-} node_type;
-
-static inline int is_WPEG(struct rio_detail *rio){
-	return (rio->type == CompatWPEG || rio->type == AltWPEG ||
-		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
-}
-
-#endif /* __ASM_SUMMIT_MPPARSE_H */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index c0b0bda754e..68b1be10cfa 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -29,21 +29,21 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *);
 /* X86_32 only */
 #ifdef CONFIG_X86_32
 /* kernel/process_32.c */
-asmlinkage int sys_fork(struct pt_regs);
-asmlinkage int sys_clone(struct pt_regs);
-asmlinkage int sys_vfork(struct pt_regs);
-asmlinkage int sys_execve(struct pt_regs);
+int sys_fork(struct pt_regs *);
+int sys_clone(struct pt_regs *);
+int sys_vfork(struct pt_regs *);
+int sys_execve(struct pt_regs *);
 
 /* kernel/signal_32.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
 			     struct old_sigaction __user *);
-asmlinkage int sys_sigaltstack(unsigned long);
-asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
+int sys_sigaltstack(struct pt_regs *);
+unsigned long sys_sigreturn(struct pt_regs *);
+long sys_rt_sigreturn(struct pt_regs *);
 
 /* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned long);
+long sys_iopl(struct pt_regs *);
 
 /* kernel/sys_i386_32.c */
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
@@ -59,8 +59,8 @@ struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
 /* kernel/vm86_32.c */
-asmlinkage int sys_vm86old(struct pt_regs);
-asmlinkage int sys_vm86(struct pt_regs);
+int sys_vm86old(struct pt_regs *);
+int sys_vm86(struct pt_regs *);
 
 #else /* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 8e626ea33a1..c00bfdbdd45 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -23,6 +23,20 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 #ifdef CONFIG_X86_32
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							\
+	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
+	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
+#define __switch_canary_oparam						\
+	, [stack_canary] "=m" (per_cpu_var(stack_canary))
+#define __switch_canary_iparam						\
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
 /*
  * Saving eflags is important. It switches not only IOPL between tasks,
  * it also protects other tasks from NT leaking through sysenter etc.
@@ -44,6 +58,7 @@ do {									\
 		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
 		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
 		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
+		     __switch_canary					\
 		     "jmp __switch_to\n"	/* regparm call  */	\
 		     "1:\t"						\
 		     "popl %%ebp\n\t"		/* restore EBP   */	\
@@ -58,6 +73,8 @@ do {									\
 		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
 		       "=S" (esi), "=D" (edi)				\
 		       							\
+		       __switch_canary_oparam				\
+									\
 		       /* input parameters: */				\
 		     : [next_sp]  "m" (next->thread.sp),		\
 		       [next_ip]  "m" (next->thread.ip),		\
@@ -66,6 +83,8 @@ do {									\
 		       [prev]     "a" (prev),				\
 		       [next]     "d" (next)				\
 									\
+		       __switch_canary_iparam				\
+									\
 		     : /* reloaded segment registers */			\
 			"memory");					\
 } while (0)
@@ -86,27 +105,44 @@ do {									\
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
 	  "r12", "r13", "r14", "r15"
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							  \
+	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
+	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam						  \
+	, [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+#define __switch_canary_iparam						  \
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
 /* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
-	asm volatile(SAVE_CONTEXT						    \
+	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
 	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
 	     "call __switch_to\n\t"					  \
 	     ".globl thread_return\n"					  \
 	     "thread_return:\n\t"					  \
-	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
+	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
+	     __switch_canary						  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 	     "movq %%rax,%%rdi\n\t" 					  \
-	     "jc   ret_from_fork\n\t"					  \
+	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"	  \
+	     "jnz   ret_from_fork\n\t"					  \
 	     RESTORE_CONTEXT						  \
 	     : "=a" (last)					  	  \
+	       __switch_canary_oparam					  \
 	     : [next] "S" (next), [prev] "D" (prev),			  \
 	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [tif_fork] "i" (TIF_FORK),			  	  \
+	       [_tif_fork] "i" (_TIF_FORK),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+	       [current_task] "m" (per_cpu_var(current_task))		  \
+	       __switch_canary_iparam					  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
@@ -165,6 +201,25 @@ extern void native_load_gs_index(unsigned);
 #define savesegment(seg, value)				\
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
+/*
+ * x86_32 user gs accessors.
+ */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_32_LAZY_GS
+#define get_user_gs(regs)	(u16)({unsigned long v; savesegment(gs, v); v;})
+#define set_user_gs(regs, v)	loadsegment(gs, (unsigned long)(v))
+#define task_user_gs(tsk)	((tsk)->thread.gs)
+#define lazy_save_gs(v)		savesegment(gs, (v))
+#define lazy_load_gs(v)		loadsegment(gs, (v))
+#else	/* X86_32_LAZY_GS */
+#define get_user_gs(regs)	(u16)((regs)->gs)
+#define set_user_gs(regs, v)	do { (regs)->gs = (v); } while (0)
+#define task_user_gs(tsk)	(task_pt_regs(tsk)->gs)
+#define lazy_save_gs(v)		do { } while (0)
+#define lazy_load_gs(v)		do { } while (0)
+#endif	/* X86_32_LAZY_GS */
+#endif	/* X86_32 */
+
 static inline unsigned long get_limit(unsigned long segment)
 {
 	unsigned long __limit;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 98789647baa..df9d5f78385 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -40,6 +40,7 @@ struct thread_info {
 						*/
 	__u8			supervisor_stack[0];
 #endif
+	int			uaccess_err;
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -194,25 +195,21 @@ static inline struct thread_info *current_thread_info(void)
 
 #else /* X86_32 */
 
-#include <asm/pda.h>
+#include <asm/percpu.h>
+#define KERNEL_STACK_OFFSET (5*8)
 
 /*
  * macros/functions for gaining access to the thread information structure
  * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
-static inline struct thread_info *current_thread_info(void)
-{
-	struct thread_info *ti;
-	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-	return ti;
-}
+DECLARE_PER_CPU(unsigned long, kernel_stack);
 
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
+static inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
-	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+	ti = (void *)(percpu_read(kernel_stack) +
+		      KERNEL_STACK_OFFSET - THREAD_SIZE);
 	return ti;
 }
 
@@ -220,8 +217,8 @@ static inline struct thread_info *stack_thread_info(void)
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg) \
-	movq %gs:pda_kernelstack,reg ; \
-	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+	movq PER_CPU_VAR(kernel_stack),reg ; \
+	subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
 
 #endif
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 0e7bbb54911..d3539f998f8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -113,7 +113,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 		__flush_tlb();
 }
 
-static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+static inline void native_flush_tlb_others(const struct cpumask *cpumask,
 					   struct mm_struct *mm,
 					   unsigned long va)
 {
@@ -142,31 +142,28 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	flush_tlb_mm(vma->vm_mm);
 }
 
-void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
-			     unsigned long va);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     struct mm_struct *mm, unsigned long va);
 
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
 
-#ifdef CONFIG_X86_32
 struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
-	char __cacheline_padding[L1_CACHE_BYTES-8];
 };
 DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
 
-void reset_lazy_tlbstate(void);
-#else
 static inline void reset_lazy_tlbstate(void)
 {
+	percpu_write(cpu_tlbstate.state, 0);
+	percpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
-#endif
 
 #endif	/* SMP */
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(&mask, mm, va)
+#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(mask, mm, va)
 #endif
 
 static inline void flush_tlb_kernel_range(unsigned long start,
@@ -175,4 +172,6 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	flush_tlb_all();
 }
 
+extern void zap_low_mappings(void);
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4e2f2e0aab2..77cfb2cfb38 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -74,6 +74,8 @@ static inline const struct cpumask *cpumask_of_node(int node)
 	return &node_to_cpumask_map[node];
 }
 
+static inline void setup_node_to_cpumask_map(void) { }
+
 #else /* CONFIG_X86_64 */
 
 /* Mappings between node number and cpus on that node. */
@@ -83,7 +85,8 @@ extern cpumask_t *node_to_cpumask_map;
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
 /* Returns the number of the current Node. */
-#define numa_node_id()		read_pda(nodenumber)
+DECLARE_PER_CPU(int, node_number);
+#define numa_node_id()		percpu_read(node_number)
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
@@ -102,10 +105,7 @@ static inline int cpu_to_node(int cpu)
 /* Same function but used if called before per_cpu areas are setup */
 static inline int early_cpu_to_node(int cpu)
 {
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	return per_cpu(x86_cpu_to_node_map, cpu);
+	return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
@@ -122,6 +122,8 @@ static inline cpumask_t node_to_cpumask(int node)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
+extern void setup_node_to_cpumask_map(void);
+
 /*
  * Replace default node_to_cpumask_ptr with optimized version
  * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
@@ -192,9 +194,20 @@ extern int __node_distance(int, int);
 
 #else /* !CONFIG_NUMA */
 
-#define numa_node_id()		0
-#define	cpu_to_node(cpu)	0
-#define	early_cpu_to_node(cpu)	0
+static inline int numa_node_id(void)
+{
+	return 0;
+}
+
+static inline int cpu_to_node(int cpu)
+{
+	return 0;
+}
+
+static inline int early_cpu_to_node(int cpu)
+{
+	return 0;
+}
 
 static inline const cpumask_t *cpumask_of_node(int node)
 {
@@ -209,6 +222,8 @@ static inline int node_to_first_cpu(int node)
 	return first_cpu(cpu_online_map);
 }
 
+static inline void setup_node_to_cpumask_map(void) { }
+
 /*
  * Replace default node_to_cpumask_ptr with optimized version
  * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0ab94f..90f06c25221 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,6 +13,7 @@ extern unsigned char *trampoline_base;
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 2ee0a3bceed..0d5342515b8 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -77,7 +77,7 @@ extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
 
 void math_error(void __user *);
-asmlinkage void math_emulate(long);
+void math_emulate(struct math_emu_info *);
 #ifdef CONFIG_X86_32
 unsigned long patch_espfix_desc(unsigned long, unsigned long);
 #else
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 4340055b755..b685ece89d5 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -121,7 +121,7 @@ extern int __get_user_bad(void);
 
 #define __get_user_x(size, ret, x, ptr)		      \
 	asm volatile("call __get_user_" #size	      \
-		     : "=a" (ret),"=d" (x)	      \
+		     : "=a" (ret), "=d" (x)	      \
 		     : "0" (ptr))		      \
 
 /* Careful: we have to cast the result to the type of the pointer
@@ -181,12 +181,12 @@ extern int __get_user_bad(void);
 
 #define __put_user_x(size, x, ptr, __ret_pu)			\
 	asm volatile("call __put_user_" #size : "=a" (__ret_pu)	\
-		     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+		     : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 
 
 
 #ifdef CONFIG_X86_32
-#define __put_user_u64(x, addr, err)					\
+#define __put_user_asm_u64(x, addr, err, errret)			\
 	asm volatile("1:	movl %%eax,0(%2)\n"			\
 		     "2:	movl %%edx,4(%2)\n"			\
 		     "3:\n"						\
@@ -197,14 +197,24 @@ extern int __get_user_bad(void);
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
 		     : "=r" (err)					\
-		     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+		     : "A" (x), "r" (addr), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex_u64(x, addr)					\
+	asm volatile("1:	movl %%eax,0(%1)\n"			\
+		     "2:	movl %%edx,4(%1)\n"			\
+		     "3:\n"						\
+		     _ASM_EXTABLE(1b, 2b - 1b)				\
+		     _ASM_EXTABLE(2b, 3b - 2b)				\
+		     : : "A" (x), "r" (addr))
 
 #define __put_user_x8(x, ptr, __ret_pu)				\
 	asm volatile("call __put_user_8" : "=a" (__ret_pu)	\
 		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 #else
-#define __put_user_u64(x, ptr, retval) \
-	__put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_asm_u64(x, ptr, retval, errret) \
+	__put_user_asm(x, ptr, retval, "q", "", "Zr", errret)
+#define __put_user_asm_ex_u64(x, addr)	\
+	__put_user_asm_ex(x, addr, "q", "", "Zr")
 #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
 #endif
 
@@ -276,10 +286,32 @@ do {									\
 		__put_user_asm(x, ptr, retval, "w", "w", "ir", errret);	\
 		break;							\
 	case 4:								\
-		__put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
+		__put_user_asm(x, ptr, retval, "l", "k", "ir", errret);	\
 		break;							\
 	case 8:								\
-		__put_user_u64((__typeof__(*ptr))(x), ptr, retval);	\
+		__put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval,	\
+				   errret);				\
+		break;							\
+	default:							\
+		__put_user_bad();					\
+	}								\
+} while (0)
+
+#define __put_user_size_ex(x, ptr, size)				\
+do {									\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__put_user_asm_ex(x, ptr, "b", "b", "iq");		\
+		break;							\
+	case 2:								\
+		__put_user_asm_ex(x, ptr, "w", "w", "ir");		\
+		break;							\
+	case 4:								\
+		__put_user_asm_ex(x, ptr, "l", "k", "ir");		\
+		break;							\
+	case 8:								\
+		__put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr);	\
 		break;							\
 	default:							\
 		__put_user_bad();					\
@@ -311,9 +343,12 @@ do {									\
 
 #ifdef CONFIG_X86_32
 #define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
+#define __get_user_asm_ex_u64(x, ptr)			(x) = __get_user_bad()
 #else
 #define __get_user_asm_u64(x, ptr, retval, errret) \
 	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#define __get_user_asm_ex_u64(x, ptr) \
+	 __get_user_asm_ex(x, ptr, "q", "", "=r")
 #endif
 
 #define __get_user_size(x, ptr, size, retval, errret)			\
@@ -350,6 +385,33 @@ do {									\
 		     : "=r" (err), ltype(x)				\
 		     : "m" (__m(addr)), "i" (errret), "0" (err))
 
+#define __get_user_size_ex(x, ptr, size)				\
+do {									\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__get_user_asm_ex(x, ptr, "b", "b", "=q");		\
+		break;							\
+	case 2:								\
+		__get_user_asm_ex(x, ptr, "w", "w", "=r");		\
+		break;							\
+	case 4:								\
+		__get_user_asm_ex(x, ptr, "l", "k", "=r");		\
+		break;							\
+	case 8:								\
+		__get_user_asm_ex_u64(x, ptr);				\
+		break;							\
+	default:							\
+		(x) = __get_user_bad();					\
+	}								\
+} while (0)
+
+#define __get_user_asm_ex(x, addr, itype, rtype, ltype)			\
+	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
+		     "2:\n"						\
+		     _ASM_EXTABLE(1b, 2b - 1b)				\
+		     : ltype(x) : "m" (__m(addr)))
+
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
 	int __pu_err;						\
@@ -385,6 +447,26 @@ struct __large_struct { unsigned long buf[100]; };
 		     _ASM_EXTABLE(1b, 3b)				\
 		     : "=r"(err)					\
 		     : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_asm_ex(x, addr, itype, rtype, ltype)			\
+	asm volatile("1:	mov"itype" %"rtype"0,%1\n"		\
+		     "2:\n"						\
+		     _ASM_EXTABLE(1b, 2b - 1b)				\
+		     : : ltype(x), "m" (__m(addr)))
+
+/*
+ * uaccess_try and catch
+ */
+#define uaccess_try	do {						\
+	int prev_err = current_thread_info()->uaccess_err;		\
+	current_thread_info()->uaccess_err = 0;				\
+	barrier();
+
+#define uaccess_catch(err)						\
+	(err) |= current_thread_info()->uaccess_err;			\
+	current_thread_info()->uaccess_err = prev_err;			\
+} while (0)
+
 /**
  * __get_user: - Get a simple variable from user space, with less checking.
  * @x:   Variable to store result.
@@ -408,6 +490,7 @@ struct __large_struct { unsigned long buf[100]; };
 
 #define __get_user(x, ptr)						\
 	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+
 /**
  * __put_user: - Write a simple value into user space, with less checking.
  * @x:   Value to copy to user space.
@@ -435,6 +518,45 @@ struct __large_struct { unsigned long buf[100]; };
 #define __put_user_unaligned __put_user
 
 /*
+ * {get|put}_user_try and catch
+ *
+ * get_user_try {
+ *	get_user_ex(...);
+ * } get_user_catch(err)
+ */
+#define get_user_try		uaccess_try
+#define get_user_catch(err)	uaccess_catch(err)
+
+#define get_user_ex(x, ptr)	do {					\
+	unsigned long __gue_val;					\
+	__get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr))));	\
+	(x) = (__force __typeof__(*(ptr)))__gue_val;			\
+} while (0)
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+#define put_user_try		uaccess_try
+#define put_user_catch(err)	uaccess_catch(err)
+
+#define put_user_ex(x, ptr)						\
+	__put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#else /* !CONFIG_X86_WP_WORKS_OK */
+
+#define put_user_try		do {		\
+	int __uaccess_err = 0;
+
+#define put_user_catch(err)			\
+	(err) |= __uaccess_err;			\
+} while (0)
+
+#define put_user_ex(x, ptr)	do {		\
+	__uaccess_err |= __put_user(x, ptr);	\
+} while (0)
+
+#endif /* CONFIG_X86_WP_WORKS_OK */
+
+/*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
 #ifdef CONFIG_X86_INTEL_USERCOPY
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
new file mode 100644
index 00000000000..8242bf96581
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_X86_UV_UV_H
+#define _ASM_X86_UV_UV_H
+
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+
+struct cpumask;
+struct mm_struct;
+
+#ifdef CONFIG_X86_UV
+
+extern enum uv_system_type get_uv_system_type(void);
+extern int is_uv_system(void);
+extern void uv_cpu_init(void);
+extern void uv_system_init(void);
+extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
+extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+						 struct mm_struct *mm,
+						 unsigned long va,
+						 unsigned int cpu);
+
+#else	/* X86_UV */
+
+static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline int is_uv_system(void)	{ return 0; }
+static inline void uv_cpu_init(void)	{ }
+static inline void uv_system_init(void)	{ }
+static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
+{ return 1; }
+static inline const struct cpumask *
+uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
+		    unsigned long va, unsigned int cpu)
+{ return cpumask; }
+
+#endif	/* X86_UV */
+
+#endif	/* _ASM_X86_UV_UV_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 50423c7b56b..9b0e61bf7a8 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,7 +325,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
 #define cpubit_isset(cpu, bau_local_cpumask) \
 	test_bit((cpu), (bau_local_cpumask).bits)
 
-extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
index b3e64730762..c1635d43616 100644
--- a/arch/x86/include/asm/voyager.h
+++ b/arch/x86/include/asm/voyager.h
@@ -527,3 +527,45 @@ extern void voyager_smp_intr_init(void);
 #define VOYAGER_PSI_SUBREAD	2
 #define VOYAGER_PSI_SUBWRITE	3
 extern void voyager_cat_psi(__u8, __u16, __u8 *);
+
+/* These define the CPIs we use in linux */
+#define VIC_CPI_LEVEL0			0
+#define VIC_CPI_LEVEL1			1
+/* now the fake CPIs */
+#define VIC_TIMER_CPI			2
+#define VIC_INVALIDATE_CPI		3
+#define VIC_RESCHEDULE_CPI		4
+#define VIC_ENABLE_IRQ_CPI		5
+#define VIC_CALL_FUNCTION_CPI		6
+#define VIC_CALL_FUNCTION_SINGLE_CPI	7
+
+/* Now the QIC CPIs:  Since we don't need the two initial levels,
+ * these are 2 less than the VIC CPIs */
+#define QIC_CPI_OFFSET			1
+#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
+#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
+#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
+#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_SINGLE_CPI	(VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
+
+#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
+#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_SINGLE_CPI
+
+/* this is the SYS_INT CPI. */
+#define VIC_SYS_INT			8
+#define VIC_CMN_INT			15
+
+/* This is the boot CPI for alternate processors.  It gets overwritten
+ * by the above once the system has activated all available processors */
+#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
+#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
+
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 19144184983..1df35417c41 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -15,10 +15,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 	return raw_irqs_disabled_flags(regs->flags);
 }
 
-static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
-{
-	regs->orig_ax = ~irq;
-	do_IRQ(regs);
-}
-
 #endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 7ef617ef1df..4bd990ee43d 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -137,7 +137,7 @@ static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
 	pte_t pte;
 
 	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
-		(pgprot_val(pgprot) & __supported_pte_mask);
+			massage_pgprot(pgprot);
 
 	return pte;
 }