Merge branch 'core/percpu' into perfcounters/core

Conflicts:
	arch/x86/include/asm/pda.h

We merge tip/core/percpu into tip/perfcounters/core because of a
semantic and contextual conflict: the former eliminates the PDA,
while the latter extends it with apic_perf_irqs field.

Resolve the conflict by moving the new field to the irq_cpustat
structure on 64-bit too.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

29 files changed, 282 insertions, 376 deletions

diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 000000000000..82f613c607ce
--- /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/bitops.h b/arch/x86/include/asm/bitops.h
index e02a359d2aa5..02b47a603fc8 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -3,6 +3,9 @@
 
 /*
  * Copyright 1992, Linus Torvalds.
+ *
+ * Note: inlines with more than a single statement should be marked
+ * __always_inline to avoid problems with older gcc's inlining heuristics.
  */
 
 #ifndef _LINUX_BITOPS_H
@@ -53,7 +56,8 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
+static __always_inline void
+set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -90,7 +94,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+clear_bit(int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -204,7 +209,8 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+static __always_inline int
+test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -300,7 +306,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return oldbit;
 }
 
-static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bae482df6039..f03b23e32864 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 +31,11 @@ extern void arch_unregister_cpu(int);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
+
+#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
+extern unsigned char boot_cpu_id;
+#else
+#define boot_cpu_id				0
+#endif
+
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
new file mode 100644
index 000000000000..26c6dad90479
--- /dev/null
+++ b/arch/x86/include/asm/cpumask.h
@@ -0,0 +1,28 @@
+#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;
+
+#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 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f8d672..c68c361697e1 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/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
index 7a07897a7888..7838276bfe51 100644
--- a/arch/x86/include/asm/hardirq_32.h
+++ b/arch/x86/include/asm/hardirq_32.h
@@ -20,6 +20,9 @@ typedef struct {
 
 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 __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
 
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
index b5a6b5d56704..42930b279215 100644
--- a/arch/x86/include/asm/hardirq_64.h
+++ b/arch/x86/include/asm/hardirq_64.h
@@ -3,22 +3,37 @@
 
 #include <linux/threads.h>
 #include <linux/irq.h>
-#include <asm/pda.h>
 #include <asm/apic.h>
 
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* arch dependent */
+	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int apic_perf_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;
+	unsigned int irq_threshold_count;
+} ____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 1
 
-#define inc_irq_stat(member)	add_pda(member, 1)
+#define inc_irq_stat(member)	percpu_add(irq_stat.member, 1)
 
-#define local_softirq_pending() read_pda(__softirq_pending)
+#define local_softirq_pending() percpu_read(irq_stat.__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))
+#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);
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7a1f44ac1f17..08ec793aa043 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;
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index 86afd7473457..d7ed33ee94e9 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -15,7 +15,7 @@ DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
 {
-	return x86_read_percpu(irq_regs);
+	return percpu_read(irq_regs);
 }
 
 static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
@@ -23,7 +23,7 @@ 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);
+	percpu_write(irq_regs, new_regs);
 
 	return old_regs;
 }
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 21a0b92027f5..1554d0236e03 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -110,6 +110,8 @@
 
 #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 
+#include <asm/apicnum.h>	/* need MAX_IO_APICS */
+
 #ifndef CONFIG_SPARSE_IRQ
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
@@ -117,11 +119,12 @@
 #  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
+
+# define NR_IRQS					\
+	((8 * NR_CPUS) > (32 * MAX_IO_APICS) ?		\
+		(NR_VECTORS + (8 * NR_CPUS)) :		\
+		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
+
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
index ceb013660146..89897a6a65b9 100644
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -24,7 +24,13 @@ 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)
 {
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
index 7e98ce1d2c0e..08b53454f831 100644
--- a/arch/x86/include/asm/mmu_context_32.h
+++ b/arch/x86/include/asm/mmu_context_32.h
@@ -4,8 +4,8 @@
 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);
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -19,8 +19,8 @@ static inline void switch_mm(struct mm_struct *prev,
 		/* 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);
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
 		cpu_set(cpu, next->cpu_vm_mask);
 
@@ -35,8 +35,8 @@ static inline void switch_mm(struct mm_struct *prev,
 	}
 #ifdef CONFIG_SMP
 	else {
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
+		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
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
index 677d36e9540a..c4572505ab3e 100644
--- a/arch/x86/include/asm/mmu_context_64.h
+++ b/arch/x86/include/asm/mmu_context_64.h
@@ -1,13 +1,11 @@
 #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);
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -19,8 +17,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *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);
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
 		cpu_set(cpu, next->cpu_vm_mask);
 		load_cr3(next->pgd);
@@ -30,9 +28,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	}
 #ifdef CONFIG_SMP
 	else {
-		write_pda(mmu_state, TLBSTATE_OK);
-		if (read_pda(active_mm) != next)
-			BUG();
+		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
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 59568bc4767f..4a7f96d7c188 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/mtrr.h b/arch/x86/include/asm/mtrr.h
index cb988aab716d..14080d22edb3 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -58,15 +58,15 @@ struct mtrr_gentry {
 #endif /* !__i386__ */
 
 struct mtrr_var_range {
-	u32 base_lo;
-	u32 base_hi;
-	u32 mask_lo;
-	u32 mask_hi;
+	__u32 base_lo;
+	__u32 base_hi;
+	__u32 mask_lo;
+	__u32 mask_hi;
 };
 
 /* In the Intel processor's MTRR interface, the MTRR type is always held in
    an 8 bit field: */
-typedef u8 mtrr_type;
+typedef __u8 mtrr_type;
 
 #define MTRR_NUM_FIXED_RANGES 88
 #define MTRR_MAX_VAR_RANGES 256
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5ebca29f44f0..e27fdbe5f9e4 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 ba3e2ff6aedc..c26c6bf4da00 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -244,7 +244,8 @@ 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 */
@@ -984,10 +985,11 @@ 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)
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
index 90a8d9d4206b..c31ca048a901 100644
--- a/arch/x86/include/asm/pda.h
+++ b/arch/x86/include/asm/pda.h
@@ -5,134 +5,41 @@
 #include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/cache.h>
+#include <linux/threads.h>
 #include <asm/page.h>
+#include <asm/percpu.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 */
+	unsigned long unused1;
+	unsigned long unused2;
+	unsigned long unused3;
+	unsigned long unused4;
+	int unused5;
+	unsigned int unused6;		/* 36 was cpunumber */
 #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 apic_perf_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;
+DECLARE_PER_CPU(struct x8664_pda, __pda);
 extern void pda_init(int);
 
-#define cpu_pda(i) (_cpu_pda[i])
+#define cpu_pda(cpu)		(&per_cpu(__pda, cpu))
 
-/*
- * 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)
+#define read_pda(field)		percpu_read(__pda.field)
+#define write_pda(field, val)	percpu_write(__pda.field, val)
+#define add_pda(field, val)	percpu_add(__pda.field, val)
+#define sub_pda(field, val)	percpu_sub(__pda.field, val)
+#define or_pda(field, val)	percpu_or(__pda.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__;								\
-})
+	x86_test_and_clear_bit_percpu(bit, __pda.field)
 
 #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 ece72053ba63..165d5272ece1 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 +24,26 @@ 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 */
 
 #else /* ...!ASSEMBLY */
 
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * 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)
- */
-#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 */
+#include <linux/stringify.h>
 
-#define __percpu_seg ""
-
-#endif	/* SMP */
-
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+#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
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
@@ -120,20 +58,25 @@ 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)			\
+		    : "r" ((T__)val));			\
+		break;					\
 	default: __bad_percpu_size();			\
 	}						\
 } while (0)
@@ -143,17 +86,22 @@ 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 +110,36 @@ 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);
+
+#ifdef CONFIG_X86_64
+extern void load_pda_offset(int cpu);
+#else
+static inline void load_pda_offset(int cpu) { }
+#endif
+
 #endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
 
 #ifdef CONFIG_SMP
 
@@ -195,9 +166,9 @@ 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 83e69f4a37f0..06bbcbd66e9c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -341,6 +341,25 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
+static inline int is_new_memtype_allowed(unsigned long flags,
+						unsigned long new_flags)
+{
+	/*
+	 * Certain new memtypes are not allowed with certain
+	 * requested memtype:
+	 * - request is uncached, return cannot be write-back
+	 * - request is write-combine, return cannot be write-back
+	 */
+	if ((flags == _PAGE_CACHE_UC_MINUS &&
+	     new_flags == _PAGE_CACHE_WB) ||
+	    (flags == _PAGE_CACHE_WC &&
+	     new_flags == _PAGE_CACHE_WB)) {
+		return 0;
+	}
+
+	return 1;
+}
+
 #ifndef __ASSEMBLY__
 /* Indicate that x86 has its own track and untrack pfn vma functions */
 #define __HAVE_PFNMAP_TRACKING
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 091cd8855f2e..f511246fa6cd 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -378,6 +378,9 @@ union thread_xstate {
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+DECLARE_PER_CPU(char[IRQ_STACK_SIZE], irq_stack);
+DECLARE_PER_CPU(char *, irq_stack_ptr);
 #endif
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858cdc8a3..536949749bc2 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -100,7 +100,6 @@ 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/smp.h b/arch/x86/include/asm/smp.h
index 19953df61c52..68636e767a91 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -17,32 +17,7 @@
 #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 +25,7 @@ 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 +140,6 @@ 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 +148,6 @@ 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 +158,11 @@ 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 +172,6 @@ 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
@@ -251,11 +214,5 @@ 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/system.h b/arch/x86/include/asm/system.h
index 8e626ea33a1a..d1dc27dba36d 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -94,7 +94,7 @@ do {									\
 	     "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"		  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
 	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 	     "movq %%rax,%%rdi\n\t" 					  \
@@ -106,7 +106,7 @@ do {									\
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
 	       [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))		  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index efdf93820aed..f38488989db7 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -196,25 +196,21 @@ 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;
 }
 
@@ -222,8 +218,8 @@ 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 0e7bbb549116..d3539f998f88 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 4e2f2e0aab27..ffea1fe03a99 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -83,7 +83,8 @@ 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 +103,7 @@ 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'. */
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0ab94f9..90f06c25221d 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/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 50423c7b56b2..74e6393bfddb 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,7 +325,8 @@ 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 int uv_flush_tlb_others(struct cpumask *,
+			       struct mm_struct *, unsigned long);
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);