Merge branch 'core/percpu' into perfcounters/core

Conflicts:
	arch/x86/include/asm/hardirq_32.h
	arch/x86/include/asm/hardirq_64.h

Semantic merge:
	arch/x86/include/asm/hardirq.h
	[ added apic_perf_irqs field. ]

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

23 files changed, 298 insertions, 318 deletions

diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
index 2c05b737ee2..4334502d366 100644
--- a/arch/x86/include/asm/genapic_32.h
+++ b/arch/x86/include/asm/genapic_32.h
@@ -138,11 +138,4 @@ struct genapic {
 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
index adf32fb56aa..7bb092c5905 100644
--- a/arch/x86/include/asm/genapic_64.h
+++ b/arch/x86/include/asm/genapic_64.h
@@ -51,15 +51,9 @@ 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);
 
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 000787df66e..46ebed797e4 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -1,11 +1,53 @@
-#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
+	unsigned int apic_perf_irqs;
+#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 7838276bfe5..00000000000
--- a/arch/x86/include/asm/hardirq_32.h
+++ /dev/null
@@ -1,34 +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 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;
-} ____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 __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 42930b27921..00000000000
--- a/arch/x86/include/asm/hardirq_64.h
+++ /dev/null
@@ -1,40 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_64_H
-#define _ASM_X86_HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.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)	percpu_add(irq_stat.member, 1)
-
-#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#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);
-
-#endif /* _ASM_X86_HARDIRQ_64_H */
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 d7ed33ee94e..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 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_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 1554d0236e0..0e2220bb314 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -49,31 +49,33 @@
  *  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
+# define RESCHEDULE_VECTOR		0xfd
+# define CALL_FUNCTION_VECTOR		0xfc
+# define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+# define THERMAL_APIC_VECTOR		0xfa
+/* 0xf8 - 0xf9 : free */
+# define INVALIDATE_TLB_VECTOR_END	0xf7
+# define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+
+# define NUM_INVALIDATE_TLB_VECTORS	8
 
 #else
 
-#define SPURIOUS_APIC_VECTOR		0xff
-#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 SPURIOUS_APIC_VECTOR		0xff
+# 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
 
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/mach-default/entry_arch.h
index ad31e5d90e9..b87b077cc23 100644
--- a/arch/x86/include/asm/mach-default/entry_arch.h
+++ b/arch/x86/include/asm/mach-default/entry_arch.h
@@ -11,10 +11,26 @@
  */
 #ifdef CONFIG_X86_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
 
 /*
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 8aeeb3fd73d..52948df9cd1 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 {						\
+	loadsegment(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 08b53454f83..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 (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)
-{
-	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
-		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.
-			 */
-			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 c4572505ab3..00000000000
--- a/arch/x86/include/asm/mmu_context_64.h
+++ /dev/null
@@ -1,52 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_64_H
-#define _ASM_X86_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);
-		load_cr3(next->pgd);
-
-		if (unlikely(next->context.ldt != prev->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 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/pda.h b/arch/x86/include/asm/pda.h
deleted file mode 100644
index c31ca048a90..00000000000
--- a/arch/x86/include/asm/pda.h
+++ /dev/null
@@ -1,45 +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 <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 {
-	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
-	short in_bootmem;		/* pda lives in bootmem */
-} ____cacheline_aligned_in_smp;
-
-DECLARE_PER_CPU(struct x8664_pda, __pda);
-extern void pda_init(int);
-
-#define cpu_pda(cpu)		(&per_cpu(__pda, cpu))
-
-#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)				\
-	x86_test_and_clear_bit_percpu(bit, __pda.field)
-
-#endif
-
-#endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 165d5272ece..0b64af4f13a 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -75,7 +75,7 @@ do {							\
 	case 8:						\
 		asm(op "q %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "r" ((T__)val));			\
+		    : "re" ((T__)val));			\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
@@ -133,12 +133,6 @@ do {							\
 /* 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__ */
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ba09289acca..1df9637dfda 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/processor.h b/arch/x86/include/asm/processor.h
index f511246fa6c..48676b943b9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -379,8 +379,29 @@ union thread_xstate {
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
 
-DECLARE_PER_CPU(char[IRQ_STACK_SIZE], irq_stack);
+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_PER_CPU(char *, irq_stack_ptr);
+
+static inline void load_gs_base(int cpu)
+{
+	/* Memory clobbers used to order pda/percpu accesses */
+	mb();
+	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+	mb();
+}
 #endif
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 68636e767a9..45ef8a1b9d7 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -15,7 +15,6 @@
 #  include <asm/io_apic.h>
 # endif
 #endif
-#include <asm/pda.h>
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
new file mode 100644
index 00000000000..36a700acaf2
--- /dev/null
+++ b/arch/x86/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <asm/tsc.h>
+#include <asm/processor.h>
+
+/*
+ * 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;
+
+	/*
+	 * Build time only check to make sure the stack_canary is at
+	 * offset 40 in the pda; this is a gcc ABI requirement
+	 */
+	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+
+	/*
+	 * 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;
+	percpu_write(irq_stack_union.stack_canary, canary);
+}
+
+#endif
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index d1dc27dba36..2fcc70bc85f 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -86,27 +86,44 @@ 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 "__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"					  \
 	     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),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
 	       [current_task] "m" (per_cpu_var(current_task))		  \
+	       __switch_canary_iparam					  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index ffea1fe03a9..10022ed3a4b 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -190,9 +190,20 @@ 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)
 {
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
new file mode 100644
index 00000000000..8ac1d7e312f
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv.h
@@ -0,0 +1,33 @@
+#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};
+
+#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 74e6393bfdd..9b0e61bf7a8 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,8 +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(struct cpumask *,
-			       struct mm_struct *, unsigned long);
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);