Merge tag 'split-asm_system_h-for-linus-20120328' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-asm_system

Pull "Disintegrate and delete asm/system.h" from David Howells:
 "Here are a bunch of patches to disintegrate asm/system.h into a set of
  separate bits to relieve the problem of circular inclusion
  dependencies.

  I've built all the working defconfigs from all the arches that I can
  and made sure that they don't break.

  The reason for these patches is that I recently encountered a circular
  dependency problem that came about when I produced some patches to
  optimise get_order() by rewriting it to use ilog2().

  This uses bitops - and on the SH arch asm/bitops.h drags in
  asm-generic/get_order.h by a circuituous route involving asm/system.h.

  The main difficulty seems to be asm/system.h.  It holds a number of
  low level bits with no/few dependencies that are commonly used (eg.
  memory barriers) and a number of bits with more dependencies that
  aren't used in many places (eg.  switch_to()).

  These patches break asm/system.h up into the following core pieces:

    (1) asm/barrier.h

        Move memory barriers here.  This already done for MIPS and Alpha.

    (2) asm/switch_to.h

        Move switch_to() and related stuff here.

    (3) asm/exec.h

        Move arch_align_stack() here.  Other process execution related bits
        could perhaps go here from asm/processor.h.

    (4) asm/cmpxchg.h

        Move xchg() and cmpxchg() here as they're full word atomic ops and
        frequently used by atomic_xchg() and atomic_cmpxchg().

    (5) asm/bug.h

        Move die() and related bits.

    (6) asm/auxvec.h

        Move AT_VECTOR_SIZE_ARCH here.

  Other arch headers are created as needed on a per-arch basis."

Fixed up some conflicts from other header file cleanups and moving code
around that has happened in the meantime, so David's testing is somewhat
weakened by that.  We'll find out anything that got broken and fix it..

* tag 'split-asm_system_h-for-linus-20120328' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-asm_system: (38 commits)
  Delete all instances of asm/system.h
  Remove all #inclusions of asm/system.h
  Add #includes needed to permit the removal of asm/system.h
  Move all declarations of free_initmem() to linux/mm.h
  Disintegrate asm/system.h for OpenRISC
  Split arch_align_stack() out from asm-generic/system.h
  Split the switch_to() wrapper out of asm-generic/system.h
  Move the asm-generic/system.h xchg() implementation to asm-generic/cmpxchg.h
  Create asm-generic/barrier.h
  Make asm-generic/cmpxchg.h #include asm-generic/cmpxchg-local.h
  Disintegrate asm/system.h for Xtensa
  Disintegrate asm/system.h for Unicore32 [based on ver #3, changed by gxt]
  Disintegrate asm/system.h for Tile
  Disintegrate asm/system.h for Sparc
  Disintegrate asm/system.h for SH
  Disintegrate asm/system.h for Score
  Disintegrate asm/system.h for S390
  Disintegrate asm/system.h for PowerPC
  Disintegrate asm/system.h for PA-RISC
  Disintegrate asm/system.h for MN10300
  ...

51 files changed, 549 insertions, 564 deletions

diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 4c2e59a420b9..d511d951a052 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9371c91718c..4b2caeefe1a2 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -11,7 +11,6 @@
 #include <linux/atomic.h>
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
-#include <asm/system.h>
 #include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h
index 1316b4c35425..77203ac352de 100644
--- a/arch/x86/include/asm/auxvec.h
+++ b/arch/x86/include/asm/auxvec.h
@@ -9,4 +9,11 @@
 #endif
 #define AT_SYSINFO_EHDR		33
 
+/* entries in ARCH_DLINFO: */
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
+# define AT_VECTOR_SIZE_ARCH 2
+#else /* else it's non-compat x86-64 */
+# define AT_VECTOR_SIZE_ARCH 1
+#endif
+
 #endif /* _ASM_X86_AUXVEC_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
new file mode 100644
index 000000000000..c6cd358a1eec
--- /dev/null
+++ b/arch/x86/include/asm/barrier.h
@@ -0,0 +1,116 @@
+#ifndef _ASM_X86_BARRIER_H
+#define _ASM_X86_BARRIER_H
+
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_X86_32
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define mb() 	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence" ::: "memory")
+#endif
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+# define smp_rmb()	rmb()
+#else
+# define smp_rmb()	barrier()
+#endif
+#ifdef CONFIG_X86_OOSTORE
+# define smp_wmb() 	wmb()
+#else
+# define smp_wmb()	barrier()
+#endif
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static __always_inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f654d1bb17fb..11e1152222d0 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -36,4 +36,8 @@ do {								\
 #endif /* !CONFIG_BUG */
 
 #include <asm-generic/bug.h>
+
+
+extern void show_regs_common(void);
+
 #endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 4e12668711e5..9863ee3747da 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -3,6 +3,7 @@
 
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_X86_PAT
 /*
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 5f962df30d0f..f27f79abe021 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -84,7 +84,6 @@ extern unsigned int vdso_enabled;
 	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_X86_32
 #include <asm/desc.h>
diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h
new file mode 100644
index 000000000000..54c2e1db274a
--- /dev/null
+++ b/arch/x86/include/asm/exec.h
@@ -0,0 +1 @@
+/* define arch_align_stack() here */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index d09bb03653f0..71ecbcba1a4e 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,7 +9,6 @@
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
 	asm volatile("1:\t" insn "\n"				\
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 7ce0798b1b26..257d9cca214f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -14,7 +14,6 @@
 
 #include <linux/sched.h>
 #include <linux/hardirq.h>
-#include <asm/system.h>
 
 struct pt_regs;
 struct user_i387_struct;
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 9cdae5d47e8f..c8bed0da434a 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -3,7 +3,6 @@
 
 #include <linux/percpu.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/asm.h>
 
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 0e8e85bb7c51..d354fb781c57 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -5,7 +5,6 @@
 #define _ASM_X86_MC146818RTC_H
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <linux/mc146818rtc.h>
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index bce688d54c12..e21fdd10479f 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
 extern void initmem_init(void);
-extern void free_initmem(void);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5533b30cac07..a19542c1685e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -14,13 +14,13 @@ struct mm_struct;
 #include <asm/sigcontext.h>
 #include <asm/current.h>
 #include <asm/cpufeature.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
+#include <asm/special_insns.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +29,15 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/irqflags.h>
+
+/*
+ * We handle most unaligned accesses in hardware.  On the other hand
+ * unaligned DMA can be quite expensive on some Nehalem processors.
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN	0
 
 #define HBP_NUM 4
 /*
@@ -959,4 +968,24 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
+#ifdef CONFIG_X86_32
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+#endif
+
+void disable_hlt(void);
+void enable_hlt(void);
+
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+bool set_pm_idle_to_default(void);
+
+void stop_this_cpu(void *dummy);
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5e641715c3fe..165466233ab0 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,7 +212,61 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
-#endif
-#endif
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg, value)						\
+do {									\
+	unsigned short __val = (value);					\
+									\
+	asm volatile("						\n"	\
+		     "1:	movl %k0,%%" #seg "		\n"	\
+									\
+		     ".section .fixup,\"ax\"			\n"	\
+		     "2:	xorl %k0,%k0			\n"	\
+		     "		jmp 1b				\n"	\
+		     ".previous					\n"	\
+									\
+		     _ASM_EXTABLE(1b, 2b)				\
+									\
+		     : "+r" (__val) : : "memory");			\
+} while (0)
+
+/*
+ * Save a segment register away
+ */
+#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;
+	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
+	return __limit + 1;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
new file mode 100644
index 000000000000..41fc93a2e225
--- /dev/null
+++ b/arch/x86/include/asm/special_insns.h
@@ -0,0 +1,199 @@
+#ifndef _ASM_X86_SPECIAL_INSNS_H
+#define _ASM_X86_SPECIAL_INSNS_H
+
+
+#ifdef __KERNEL__
+
+static inline void native_clts(void)
+{
+	asm volatile("clts");
+}
+
+/*
+ * Volatile isn't enough to prevent the compiler from reordering the
+ * read/write functions for the control registers and messing everything up.
+ * A memory clobber would solve the problem, but would prevent reordering of
+ * all loads stores around it, which can hurt performance. Solution is to
+ * use a variable and mimic reads and writes to it to enforce serialization
+ */
+static unsigned long __force_order;
+
+static inline unsigned long native_read_cr0(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+	unsigned long val;
+	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
+	 * exists, so it will never fail. */
+#ifdef CONFIG_X86_32
+	asm volatile("1: mov %%cr4, %0\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b, 2b)
+		     : "=r" (val), "=m" (__force_order) : "0" (0));
+#else
+	val = native_read_cr4();
+#endif
+	return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long native_read_cr8(void)
+{
+	unsigned long cr8;
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
+	return cr8;
+}
+
+static inline void native_write_cr8(unsigned long val)
+{
+	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+#endif
+
+static inline void native_wbinvd(void)
+{
+	asm volatile("wbinvd": : :"memory");
+}
+
+extern void native_load_gs_index(unsigned);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+
+static inline unsigned long read_cr0(void)
+{
+	return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+	native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+	return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+	native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+	return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+	native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+	return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+	return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+	native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+	native_wbinvd();
+}
+
+#ifdef CONFIG_X86_64
+
+static inline unsigned long read_cr8(void)
+{
+	return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+	native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+	native_load_gs_index(selector);
+}
+
+#endif
+
+/* Clear the 'TS' bit */
+static inline void clts(void)
+{
+	native_clts();
+}
+
+#endif/* CONFIG_PARAVIRT */
+
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
+
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
+}
+
+#define nop() asm volatile ("nop")
+
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 157517763565..b5d9533d2c38 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -38,7 +38,6 @@
 #include <asm/tsc.h>
 #include <asm/processor.h>
 #include <asm/percpu.h>
-#include <asm/system.h>
 #include <asm/desc.h>
 #include <linux/random.h>
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
new file mode 100644
index 000000000000..4ec45b3abba1
--- /dev/null
+++ b/arch/x86/include/asm/switch_to.h
@@ -0,0 +1,129 @@
+#ifndef _ASM_X86_SWITCH_TO_H
+#define _ASM_X86_SWITCH_TO_H
+
+struct task_struct; /* one of the stranger aspects of C forward declarations */
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
+struct tss_struct;
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+		      struct tss_struct *tss);
+
+#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" (stack_canary.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.
+ */
+#define switch_to(prev, next, last)					\
+do {									\
+	/*								\
+	 * Context-switching clobbers all registers, so we clobber	\
+	 * them explicitly, via unused output variables.		\
+	 * (EAX and EBP is not listed because EBP is saved/restored	\
+	 * explicitly for wchan access and EAX is the return value of	\
+	 * __switch_to())						\
+	 */								\
+	unsigned long ebx, ecx, edx, esi, edi;				\
+									\
+	asm volatile("pushfl\n\t"		/* save    flags */	\
+		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
+		     "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   */	\
+		     "popfl\n"			/* restore flags */	\
+									\
+		     /* output parameters */				\
+		     : [prev_sp] "=m" (prev->thread.sp),		\
+		       [prev_ip] "=m" (prev->thread.ip),		\
+		       "=a" (last),					\
+									\
+		       /* clobbered output registers: */		\
+		       "=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),		\
+		       							\
+		       /* regparm parameters for __switch_to(): */	\
+		       [prev]     "a" (prev),				\
+		       [next]     "d" (next)				\
+									\
+		       __switch_canary_iparam				\
+									\
+		     : /* reloaded segment registers */			\
+			"memory");					\
+} while (0)
+
+#else /* CONFIG_X86_32 */
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER  \
+	, "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" (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					  \
+	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
+	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
+	     "call __switch_to\n\t"					  \
+	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
+	     __switch_canary						  \
+	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
+	     "movq %%rax,%%rdi\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),			  	  \
+	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
+	       [current_task] "m" (current_task)			  \
+	       __switch_canary_iparam					  \
+	     : "memory", "cc" __EXTRA_CLOBBER)
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
deleted file mode 100644
index 2d2f01ce6dcb..000000000000
--- a/arch/x86/include/asm/system.h
+++ /dev/null
@@ -1,523 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H
-#define _ASM_X86_SYSTEM_H
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
-# define AT_VECTOR_SIZE_ARCH 2
-#else /* else it's non-compat x86-64 */
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
-				struct task_struct *next);
-struct tss_struct;
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
-		      struct tss_struct *tss);
-extern void show_regs_common(void);
-
-#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" (stack_canary.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.
- */
-#define switch_to(prev, next, last)					\
-do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "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   */	\
-		     "popfl\n"			/* restore flags */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=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),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
-									\
-		       __switch_canary_iparam				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
-} while (0)
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#else
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
-
-#define __EXTRA_CLOBBER  \
-	, "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" (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					  \
-	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
-	     __switch_canary						  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     "movq %%rax,%%rdi\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),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (current_task)			  \
-	       __switch_canary_iparam					  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-#endif
-
-#ifdef __KERNEL__
-
-extern void native_load_gs_index(unsigned);
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg, value)						\
-do {									\
-	unsigned short __val = (value);					\
-									\
-	asm volatile("						\n"	\
-		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
-		     : "+r" (__val) : : "memory");			\
-} while (0)
-
-/*
- * Save a segment register away
- */
-#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;
-	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
-	return __limit + 1;
-}
-
-static inline void native_clts(void)
-{
-	asm volatile("clts");
-}
-
-/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
- */
-static unsigned long __force_order;
-
-static inline unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr0(unsigned long val)
-{
-	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr2(unsigned long val)
-{
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr3(unsigned long val)
-{
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
-	 * exists, so it will never fail. */
-#ifdef CONFIG_X86_32
-	asm volatile("1: mov %%cr4, %0\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
-#else
-	val = native_read_cr4();
-#endif
-	return val;
-}
-
-static inline void native_write_cr4(unsigned long val)
-{
-	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long native_read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void native_write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-#endif
-
-static inline void native_wbinvd(void)
-{
-	asm volatile("wbinvd": : :"memory");
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-
-static inline unsigned long read_cr0(void)
-{
-	return native_read_cr0();
-}
-
-static inline void write_cr0(unsigned long x)
-{
-	native_write_cr0(x);
-}
-
-static inline unsigned long read_cr2(void)
-{
-	return native_read_cr2();
-}
-
-static inline void write_cr2(unsigned long x)
-{
-	native_write_cr2(x);
-}
-
-static inline unsigned long read_cr3(void)
-{
-	return native_read_cr3();
-}
-
-static inline void write_cr3(unsigned long x)
-{
-	native_write_cr3(x);
-}
-
-static inline unsigned long read_cr4(void)
-{
-	return native_read_cr4();
-}
-
-static inline unsigned long read_cr4_safe(void)
-{
-	return native_read_cr4_safe();
-}
-
-static inline void write_cr4(unsigned long x)
-{
-	native_write_cr4(x);
-}
-
-static inline void wbinvd(void)
-{
-	native_wbinvd();
-}
-
-#ifdef CONFIG_X86_64
-
-static inline unsigned long read_cr8(void)
-{
-	return native_read_cr8();
-}
-
-static inline void write_cr8(unsigned long x)
-{
-	native_write_cr8(x);
-}
-
-static inline void load_gs_index(unsigned selector)
-{
-	native_load_gs_index(selector);
-}
-
-#endif
-
-/* Clear the 'TS' bit */
-static inline void clts(void)
-{
-	native_clts();
-}
-
-#endif/* CONFIG_PARAVIRT */
-
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
-#endif /* __KERNEL__ */
-
-static inline void clflush(volatile void *__p)
-{
-	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
-}
-
-#define nop() asm volatile ("nop")
-
-void disable_hlt(void);
-void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
-
-void default_idle(void);
-bool set_pm_idle_to_default(void);
-
-void stop_this_cpu(void *dummy);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static __always_inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-/*
- * We handle most unaligned accesses in hardware.  On the other hand
- * unaligned DMA can be quite expensive on some Nehalem processors.
- *
- * Based on this we disable the IP header alignment in network drivers.
- */
-#define NET_IP_ALIGN	0
-#endif /* _ASM_X86_SYSTEM_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 169be8938b96..c0e108e08079 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,7 +5,7 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index e0f9aa16358b..5da71c27cc59 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -16,7 +16,6 @@
 #define _ASM_X86_VIRTEX_H
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #include <asm/vmx.h>
 #include <asm/svm.h>
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index f50e7fb2a201..d2b7f27781bc 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -14,6 +14,7 @@
 #include <acpi/processor.h>
 #include <asm/acpi.h>
 #include <asm/mwait.h>
+#include <asm/special_insns.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d56931a15b3..459e78cbf61e 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -231,7 +231,6 @@
 #include <linux/syscore_ops.h>
 #include <linux/i8253.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/olpc.h>
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 5c0e6533d9bc..2d5454cd2c4f 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -9,7 +9,6 @@
 #include <linux/smp.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 67bb17a37a0a..47a1870279aa 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -25,7 +25,6 @@
 #include <linux/cpu.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/idle.h>
 #include <asm/mce.h>
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 54060f565974..2d7998fb628c 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -8,7 +8,6 @@
 #include <linux/init.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 97b26356e9ee..75772ae6c65f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -12,7 +12,6 @@
 #include <asm/processor-flags.h>
 #include <asm/cpufeature.h>
 #include <asm/tlbflush.h>
-#include <asm/system.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/pat.h>
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index a524353d93f2..39472dd2323f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -43,7 +43,6 @@
 
 #include <asm/processor.h>
 #include <asm/msr.h>
-#include <asm/system.h>
 
 static struct class *cpuid_class;
 
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 610485223bdb..36d1853e91af 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -15,7 +15,6 @@
 #include <linux/delay.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 43e2b1cff0a7..6d5fc8cfd5d6 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index fdc37b3d0ce3..db6720edfdd0 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -46,7 +46,6 @@
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ea697263b373..ebc987398923 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index a3fa43ba5d3b..5b19e4d78b00 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -23,7 +23,6 @@
 #include <asm/apic.h>
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/debugreg.h>
 
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 177183cbb6ae..7eb1e2b97827 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -43,7 +43,6 @@
 #include <linux/mca.h>
 #include <linux/kprobes.h>
 #include <linux/slab.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <linux/proc_fs.h>
 #include <linux/mman.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 925179f871de..f21fd94ac897 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -26,7 +26,6 @@
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 96356762a51d..eb113693f043 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,6 @@
 
 #include <asm/processor.h>
 #include <asm/msr.h>
-#include <asm/system.h>
 
 static struct class *msr_class;
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9c57c02e54f6..ab137605e694 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -38,6 +38,7 @@
 #include <asm/apic.h>
 #include <asm/tlbflush.h>
 #include <asm/timer.h>
+#include <asm/special_insns.h>
 
 /* nop stub */
 void _paravirt_nop(void)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 726494b58345..6ac5782f4d6b 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -42,7 +42,6 @@
 #include <asm/calgary.h>
 #include <asm/tce.h>
 #include <asm/pci-direct.h>
-#include <asm/system.h>
 #include <asm/dma.h>
 #include <asm/rio.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 14baf78d5a1f..9b24f36eb55f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -15,7 +15,6 @@
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/cpu.h>
-#include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
 #include <asm/idle.h>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9d7d4842bfaf..aae4f4bbbe88 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -41,7 +41,6 @@
 #include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
@@ -59,6 +58,7 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
+#include <asm/switch_to.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 292da13fc5aa..61270e8d428a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -40,7 +40,6 @@
 #include <linux/cpuidle.h>
 
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
@@ -53,6 +52,7 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
+#include <asm/switch_to.h>
 
 asmlinkage extern void ret_from_fork(void);
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 78f05e438be5..8a634c887652 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -24,7 +24,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 88638883176a..8cbeb7209c3e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -90,7 +90,6 @@
 #include <asm/processor.h>
 #include <asm/bugs.h>
 
-#include <asm/system.h>
 #include <asm/vsyscall.h>
 #include <asm/cpu.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index 9e540fee7009..ab40954e113e 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -34,6 +34,7 @@
 #include <asm/tce.h>
 #include <asm/calgary.h>
 #include <asm/proto.h>
+#include <asm/cacheflush.h>
 
 /* flush a tce at 'tceaddr' to main memory */
 static inline void flush_tce(void* tceaddr)
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6bb7b8579e70..73920e4c6dc5 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -6,7 +6,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/desc.h>
-#include <asm/system.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ec61d4c1b93b..860f126ca233 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,7 +50,6 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
-#include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 6cabf6570d64..4f0cec7e4ffb 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -12,7 +12,6 @@
 #include <asm/page_types.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
-#include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include <asm/proto.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8663f6c47ccb..575d86f85ce4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -35,7 +35,6 @@
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/dma.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 436a0309db33..fc18be0f6f29 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -35,7 +35,6 @@
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index cac718499256..a69bcb8c7621 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -10,7 +10,6 @@
 #include <linux/spinlock.h>
 #include <linux/module.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 3769079874d8..74202c1910cd 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -10,7 +10,6 @@
 #include <linux/suspend.h>
 #include <linux/bootmem.h>
 
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>