Merge branch 'x86/unify-lib' into x86/core

13 files changed, 118 insertions, 389 deletions

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 3d22bb8175b4..abff1b84ed5b 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -344,7 +344,7 @@ config X86_F00F_BUG
 
 config X86_WP_WORKS_OK
         def_bool y
-        depends on X86_32 && !M386
+        depends on !M386
 
 config X86_INVLPG
         def_bool y
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 24e4d4928d65..20371d0635e4 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -116,7 +116,7 @@ ENTRY(ia32_sysenter_target)
         pushfq
         CFI_ADJUST_CFA_OFFSET 8
         /*CFI_REL_OFFSET rflags,0*/
-        movl    8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d
+        movl    8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d
         CFI_REGISTER rip,r10
         pushq   $__USER32_CS
         CFI_ADJUST_CFA_OFFSET 8
@@ -136,8 +136,9 @@ ENTRY(ia32_sysenter_target)
         .quad 1b,ia32_badarg
         .previous       
         GET_THREAD_INFO(%r10)
-        orl    $TS_COMPAT,threadinfo_status(%r10)
-        testl  $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+        orl    $TS_COMPAT,TI_status(%r10)
+        testl  $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+                 TI_flags(%r10)
         CFI_REMEMBER_STATE
         jnz  sysenter_tracesys
 sysenter_do_call:       
@@ -149,9 +150,9 @@ sysenter_do_call:
         GET_THREAD_INFO(%r10)
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
-        testl   $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+        testl   $_TIF_ALLWORK_MASK,TI_flags(%r10)
         jnz     int_ret_from_sys_call
-        andl    $~TS_COMPAT,threadinfo_status(%r10)
+        andl    $~TS_COMPAT,TI_status(%r10)
         /* clear IF, that popfq doesn't enable interrupts early */
         andl  $~0x200,EFLAGS-R11(%rsp) 
         movl    RIP-R11(%rsp),%edx              /* User %eip */
@@ -240,8 +241,9 @@ ENTRY(ia32_cstar_target)
         .quad 1b,ia32_badarg
         .previous       
         GET_THREAD_INFO(%r10)
-        orl   $TS_COMPAT,threadinfo_status(%r10)
-        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+        orl   $TS_COMPAT,TI_status(%r10)
+        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+                TI_flags(%r10)
         CFI_REMEMBER_STATE
         jnz   cstar_tracesys
 cstar_do_call:  
@@ -253,9 +255,9 @@ cstar_do_call:
         GET_THREAD_INFO(%r10)
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
-        testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
+        testl $_TIF_ALLWORK_MASK,TI_flags(%r10)
         jnz  int_ret_from_sys_call
-        andl $~TS_COMPAT,threadinfo_status(%r10)
+        andl $~TS_COMPAT,TI_status(%r10)
         RESTORE_ARGS 1,-ARG_SKIP,1,1,1
         movl RIP-ARGOFFSET(%rsp),%ecx
         CFI_REGISTER rip,rcx
@@ -333,8 +335,9 @@ ENTRY(ia32_syscall)
            this could be a problem. */
         SAVE_ARGS 0,0,1
         GET_THREAD_INFO(%r10)
-        orl   $TS_COMPAT,threadinfo_status(%r10)
-        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
+        orl   $TS_COMPAT,TI_status(%r10)
+        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+                TI_flags(%r10)
         jnz ia32_tracesys
 ia32_do_syscall:        
         cmpl $(IA32_NR_syscalls-1),%eax
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 3295e7c08fe7..bacf5deeec2d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -34,7 +34,7 @@ int main(void)
         ENTRY(pid);
         BLANK();
 #undef ENTRY
-#define ENTRY(entry) DEFINE(threadinfo_ ## entry, offsetof(struct thread_info, entry))
+#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
         ENTRY(flags);
         ENTRY(addr_limit);
         ENTRY(preempt_count);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 07d69f262337..466b9284ed2f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -168,13 +168,13 @@ ENTRY(ret_from_fork)
         CFI_ADJUST_CFA_OFFSET -4
         call schedule_tail
         GET_THREAD_INFO(%rcx)
-        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
         jnz rff_trace
 rff_action:     
         RESTORE_REST
         testl $3,CS-ARGOFFSET(%rsp)     # from kernel_thread?
         je   int_ret_from_sys_call
-        testl $_TIF_IA32,threadinfo_flags(%rcx)
+        testl $_TIF_IA32,TI_flags(%rcx)
         jnz  int_ret_from_sys_call
         RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
         jmp ret_from_sys_call
@@ -243,7 +243,8 @@ ENTRY(system_call_after_swapgs)
         movq  %rcx,RIP-ARGOFFSET(%rsp)
         CFI_REL_OFFSET rip,RIP-ARGOFFSET
         GET_THREAD_INFO(%rcx)
-        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx)
+        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+                TI_flags(%rcx)
         jnz tracesys
         cmpq $__NR_syscall_max,%rax
         ja badsys
@@ -262,7 +263,7 @@ sysret_check:
         GET_THREAD_INFO(%rcx)
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
-        movl threadinfo_flags(%rcx),%edx
+        movl TI_flags(%rcx),%edx
         andl %edi,%edx
         jnz  sysret_careful 
         CFI_REMEMBER_STATE
@@ -347,10 +348,10 @@ int_ret_from_sys_call:
 int_with_check:
         LOCKDEP_SYS_EXIT_IRQ
         GET_THREAD_INFO(%rcx)
-        movl threadinfo_flags(%rcx),%edx
+        movl TI_flags(%rcx),%edx
         andl %edi,%edx
         jnz   int_careful
-        andl    $~TS_COMPAT,threadinfo_status(%rcx)
+        andl    $~TS_COMPAT,TI_status(%rcx)
         jmp   retint_swapgs
 
         /* Either reschedule or signal or syscall exit tracking needed. */
@@ -558,7 +559,7 @@ retint_with_reschedule:
         movl $_TIF_WORK_MASK,%edi
 retint_check:
         LOCKDEP_SYS_EXIT_IRQ
-        movl threadinfo_flags(%rcx),%edx
+        movl TI_flags(%rcx),%edx
         andl %edi,%edx
         CFI_REMEMBER_STATE
         jnz  retint_careful
@@ -654,9 +655,9 @@ retint_signal:
         /* Returning to kernel space. Check if we need preemption */
         /* rcx:  threadinfo. interrupts off. */
 ENTRY(retint_kernel)
-        cmpl $0,threadinfo_preempt_count(%rcx)
+        cmpl $0,TI_preempt_count(%rcx)
         jnz  retint_restore_args
-        bt  $TIF_NEED_RESCHED,threadinfo_flags(%rcx)
+        bt  $TIF_NEED_RESCHED,TI_flags(%rcx)
         jnc  retint_restore_args
         bt   $9,EFLAGS-ARGOFFSET(%rsp)  /* interrupts off? */
         jnc  retint_restore_args
@@ -819,7 +820,7 @@ paranoid_restore\trace:
         jmp irq_return
 paranoid_userspace\trace:
         GET_THREAD_INFO(%rcx)
-        movl threadinfo_flags(%rcx),%ebx
+        movl TI_flags(%rcx),%ebx
         andl $_TIF_WORK_MASK,%ebx
         jz paranoid_swapgs\trace
         movq %rsp,%rdi                  /* &pt_regs */
@@ -917,7 +918,7 @@ error_exit:
         testl %eax,%eax
         jne  retint_kernel
         LOCKDEP_SYS_EXIT_IRQ
-        movl  threadinfo_flags(%rcx),%edx
+        movl  TI_flags(%rcx),%edx
         movl  $_TIF_WORK_MASK,%edi
         andl  %edi,%edx
         jnz  retint_careful
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3c36f92160c9..4a775d001957 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -513,6 +513,7 @@ void __init tsc_init(void)
          */
         for_each_possible_cpu(cpu)
                 set_cyc2ns_scale(cpu_khz, cpu);
+        use_tsc_delay();
 
         if (tsc_disabled > 0)
                 return;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 76f60f52a885..83226e0a7ce4 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -4,8 +4,8 @@
 
 obj-$(CONFIG_SMP) := msr-on-cpu.o
 
-lib-y := delay_$(BITS).o
-lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o
+lib-y := delay.o
+lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 
 ifeq ($(CONFIG_X86_32),y)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index ee1c3f635157..7eaaf0123b4d 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -40,7 +40,7 @@ ENTRY(copy_to_user)
         movq %rdi,%rcx
         addq %rdx,%rcx
         jc  bad_to_user
-        cmpq threadinfo_addr_limit(%rax),%rcx
+        cmpq TI_addr_limit(%rax),%rcx
         jae bad_to_user
         xorl %eax,%eax  /* clear zero flag */
         ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
@@ -65,7 +65,7 @@ ENTRY(copy_from_user)
         movq %rsi,%rcx
         addq %rdx,%rcx
         jc  bad_from_user
-        cmpq threadinfo_addr_limit(%rax),%rcx
+        cmpq TI_addr_limit(%rax),%rcx
         jae  bad_from_user
         movl $1,%ecx    /* set zero flag */
         ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay.c
index ef691316f8b6..f4568605d7d5 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay.c
@@ -29,7 +29,7 @@
 /* simple loop based delay: */
 static void delay_loop(unsigned long loops)
 {
-        __asm__ __volatile__(
+        asm volatile(
                 "       test %0,%0      \n"
                 "       jz 3f           \n"
                 "       jmp 1f          \n"
@@ -38,9 +38,9 @@ static void delay_loop(unsigned long loops)
                 "1:     jmp 2f          \n"
 
                 ".align 16              \n"
-                "2:     decl %0         \n"
+                "2:     dec %0          \n"
                 "       jnz 2b          \n"
-                "3:     decl %0         \n"
+                "3:     dec %0          \n"
 
                 : /* we don't need output */
                 :"a" (loops)
@@ -98,7 +98,7 @@ void use_tsc_delay(void)
 int __devinit read_current_timer(unsigned long *timer_val)
 {
         if (delay_fn == delay_tsc) {
-                rdtscl(*timer_val);
+                rdtscll(*timer_val);
                 return 0;
         }
         return -1;
@@ -108,31 +108,30 @@ void __delay(unsigned long loops)
 {
         delay_fn(loops);
 }
+EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
         int d0;
 
         xloops *= 4;
-        __asm__("mull %0"
+        asm("mull %%edx"
                 :"=d" (xloops), "=&a" (d0)
                 :"1" (xloops), "0"
                 (cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
 
         __delay(++xloops);
 }
+EXPORT_SYMBOL(__const_udelay);
 
 void __udelay(unsigned long usecs)
 {
         __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
 }
+EXPORT_SYMBOL(__udelay);
 
 void __ndelay(unsigned long nsecs)
 {
         __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
 }
-
-EXPORT_SYMBOL(__delay);
-EXPORT_SYMBOL(__const_udelay);
-EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__ndelay);
diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c
deleted file mode 100644
index 4c441be92641..000000000000
--- a/arch/x86/lib/delay_64.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- *      Precise Delay Loops for x86-64
- *
- *      Copyright (C) 1993 Linus Torvalds
- *      Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
- *
- *      The __delay function must _NOT_ be inlined as its execution time
- *      depends wildly on alignment on many x86 processors. 
- */
-
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/timex.h>
-#include <linux/preempt.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-
-#include <asm/delay.h>
-#include <asm/msr.h>
-
-#ifdef CONFIG_SMP
-#include <asm/smp.h>
-#endif
-
-int __devinit read_current_timer(unsigned long *timer_value)
-{
-        rdtscll(*timer_value);
-        return 0;
-}
-
-void __delay(unsigned long loops)
-{
-        unsigned bclock, now;
-        int cpu;
-
-        preempt_disable();
-        cpu = smp_processor_id();
-        rdtscl(bclock);
-        for (;;) {
-                rdtscl(now);
-                if ((now - bclock) >= loops)
-                        break;
-
-                /* Allow RT tasks to run */
-                preempt_enable();
-                rep_nop();
-                preempt_disable();
-
-                /*
-                 * It is possible that we moved to another CPU, and
-                 * since TSC's are per-cpu we need to calculate
-                 * that. The delay must guarantee that we wait "at
-                 * least" the amount of time. Being moved to another
-                 * CPU could make the wait longer but we just need to
-                 * make sure we waited long enough. Rebalance the
-                 * counter for this CPU.
-                 */
-                if (unlikely(cpu != smp_processor_id())) {
-                        loops -= (now - bclock);
-                        cpu = smp_processor_id();
-                        rdtscl(bclock);
-                }
-        }
-        preempt_enable();
-}
-EXPORT_SYMBOL(__delay);
-
-inline void __const_udelay(unsigned long xloops)
-{
-        __delay(((xloops * HZ *
-                cpu_data(raw_smp_processor_id()).loops_per_jiffy) >> 32) + 1);
-}
-EXPORT_SYMBOL(__const_udelay);
-
-void __udelay(unsigned long usecs)
-{
-        __const_udelay(usecs * 0x000010c7);  /* 2**32 / 1000000 (rounded up) */
-}
-EXPORT_SYMBOL(__udelay);
-
-void __ndelay(unsigned long nsecs)
-{
-        __const_udelay(nsecs * 0x00005);  /* 2**32 / 1000000000 (rounded up) */
-}
-EXPORT_SYMBOL(__ndelay);
diff --git a/arch/x86/lib/getuser_64.S b/arch/x86/lib/getuser.S
index 5448876261f8..ad374003742f 100644
--- a/arch/x86/lib/getuser_64.S
+++ b/arch/x86/lib/getuser.S
@@ -3,6 +3,7 @@
  *
  * (C) Copyright 1998 Linus Torvalds
  * (C) Copyright 2005 Andi Kleen
+ * (C) Copyright 2008 Glauber Costa
  *
  * These functions have a non-standard call interface
  * to make them more efficient, especially as they
@@ -13,14 +14,13 @@
 /*
  * __get_user_X
  *
- * Inputs:      %rcx contains the address.
+ * Inputs:      %[r|e]ax contains the address.
  *              The register is modified, but all changes are undone
  *              before returning because the C code doesn't know about it.
  *
- * Outputs:     %rax is error code (0 or -EFAULT)
- *              %rdx contains zero-extended value
- * 
- * %r8 is destroyed.
+ * Outputs:     %[r|e]ax is error code (0 or -EFAULT)
+ *              %[r|e]dx contains zero-extended value
+ *
  *
  * These functions should not modify any other registers,
  * as they get called from within inline assembly.
@@ -32,78 +32,73 @@
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
+#include <asm/asm.h>
 
         .text
 ENTRY(__get_user_1)
         CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        cmpq threadinfo_addr_limit(%r8),%rcx
+        GET_THREAD_INFO(%_ASM_DX)
+        cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
         jae bad_get_user
-1:      movzb (%rcx),%edx
-        xorl %eax,%eax
+1:      movzb (%_ASM_AX),%edx
+        xor %eax,%eax
         ret
         CFI_ENDPROC
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
         CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $1,%rcx
-        jc 20f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae 20f
-        decq   %rcx
-2:      movzwl (%rcx),%edx
-        xorl %eax,%eax
+        add $1,%_ASM_AX
+        jc bad_get_user
+        GET_THREAD_INFO(%_ASM_DX)
+        cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+        jae bad_get_user
+2:      movzwl -1(%_ASM_AX),%edx
+        xor %eax,%eax
         ret
-20:     decq    %rcx
-        jmp     bad_get_user
         CFI_ENDPROC
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
         CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $3,%rcx
-        jc 30f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae 30f
-        subq $3,%rcx
-3:      movl (%rcx),%edx
-        xorl %eax,%eax
+        add $3,%_ASM_AX
+        jc bad_get_user
+        GET_THREAD_INFO(%_ASM_DX)
+        cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+        jae bad_get_user
+3:      mov -3(%_ASM_AX),%edx
+        xor %eax,%eax
         ret
-30:     subq $3,%rcx
-        jmp bad_get_user
         CFI_ENDPROC
 ENDPROC(__get_user_4)
 
+#ifdef CONFIG_X86_64
 ENTRY(__get_user_8)
         CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $7,%rcx
-        jc 40f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae     40f
-        subq    $7,%rcx
-4:      movq (%rcx),%rdx
-        xorl %eax,%eax
+        add $7,%_ASM_AX
+        jc bad_get_user
+        GET_THREAD_INFO(%_ASM_DX)
+        cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+        jae     bad_get_user
+4:      movq -7(%_ASM_AX),%_ASM_DX
+        xor %eax,%eax
         ret
-40:     subq $7,%rcx
-        jmp bad_get_user
         CFI_ENDPROC
 ENDPROC(__get_user_8)
+#endif
 
 bad_get_user:
         CFI_STARTPROC
-        xorl %edx,%edx
-        movq $(-EFAULT),%rax
+        xor %edx,%edx
+        mov $(-EFAULT),%_ASM_AX
         ret
         CFI_ENDPROC
 END(bad_get_user)
 
 .section __ex_table,"a"
-        .quad 1b,bad_get_user
-        .quad 2b,bad_get_user
-        .quad 3b,bad_get_user
-        .quad 4b,bad_get_user
-.previous
+        _ASM_PTR 1b,bad_get_user
+        _ASM_PTR 2b,bad_get_user
+        _ASM_PTR 3b,bad_get_user
+#ifdef CONFIG_X86_64
+        _ASM_PTR 4b,bad_get_user
+#endif
diff --git a/arch/x86/lib/getuser_32.S b/arch/x86/lib/getuser_32.S
deleted file mode 100644
index 6d84b53f12a2..000000000000
--- a/arch/x86/lib/getuser_32.S
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * __get_user functions.
- *
- * (C) Copyright 1998 Linus Torvalds
- *
- * These functions have a non-standard call interface
- * to make them more efficient, especially as they
- * return an error value in addition to the "real"
- * return value.
- */
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/thread_info.h>
-
-
-/*
- * __get_user_X
- *
- * Inputs:      %eax contains the address
- *
- * Outputs:     %eax is error code (0 or -EFAULT)
- *              %edx contains zero-extended value
- *
- * These functions should not modify any other registers,
- * as they get called from within inline assembly.
- */
-
-.text
-ENTRY(__get_user_1)
-        CFI_STARTPROC
-        GET_THREAD_INFO(%edx)
-        cmpl TI_addr_limit(%edx),%eax
-        jae bad_get_user
-1:      movzbl (%eax),%edx
-        xorl %eax,%eax
-        ret
-        CFI_ENDPROC
-ENDPROC(__get_user_1)
-
-ENTRY(__get_user_2)
-        CFI_STARTPROC
-        addl $1,%eax
-        jc bad_get_user
-        GET_THREAD_INFO(%edx)
-        cmpl TI_addr_limit(%edx),%eax
-        jae bad_get_user
-2:      movzwl -1(%eax),%edx
-        xorl %eax,%eax
-        ret
-        CFI_ENDPROC
-ENDPROC(__get_user_2)
-
-ENTRY(__get_user_4)
-        CFI_STARTPROC
-        addl $3,%eax
-        jc bad_get_user
-        GET_THREAD_INFO(%edx)
-        cmpl TI_addr_limit(%edx),%eax
-        jae bad_get_user
-3:      movl -3(%eax),%edx
-        xorl %eax,%eax
-        ret
-        CFI_ENDPROC
-ENDPROC(__get_user_4)
-
-bad_get_user:
-        CFI_STARTPROC
-        xorl %edx,%edx
-        movl $-14,%eax
-        ret
-        CFI_ENDPROC
-END(bad_get_user)
-
-.section __ex_table,"a"
-        .long 1b,bad_get_user
-        .long 2b,bad_get_user
-        .long 3b,bad_get_user
-.previous
diff --git a/arch/x86/lib/putuser_32.S b/arch/x86/lib/putuser.S
index f58fba109d18..36b0d15ae6e9 100644
--- a/arch/x86/lib/putuser_32.S
+++ b/arch/x86/lib/putuser.S
@@ -2,6 +2,8 @@
  * __put_user functions.
  *
  * (C) Copyright 2005 Linus Torvalds
+ * (C) Copyright 2005 Andi Kleen
+ * (C) Copyright 2008 Glauber Costa
  *
  * These functions have a non-standard call interface
  * to make them more efficient, especially as they
@@ -11,6 +13,8 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/thread_info.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
 
 
 /*
@@ -26,73 +30,68 @@
  */
 
 #define ENTER   CFI_STARTPROC ; \
-                pushl %ebx ; \
-                CFI_ADJUST_CFA_OFFSET 4 ; \
-                CFI_REL_OFFSET ebx, 0 ; \
-                GET_THREAD_INFO(%ebx)
-#define EXIT    popl %ebx ; \
-                CFI_ADJUST_CFA_OFFSET -4 ; \
-                CFI_RESTORE ebx ; \
-                ret ; \
+                GET_THREAD_INFO(%_ASM_BX)
+#define EXIT    ret ; \
                 CFI_ENDPROC
 
 .text
 ENTRY(__put_user_1)
         ENTER
-        cmpl TI_addr_limit(%ebx),%ecx
+        cmp TI_addr_limit(%_ASM_BX),%_ASM_CX
         jae bad_put_user
-1:      movb %al,(%ecx)
-        xorl %eax,%eax
+1:      movb %al,(%_ASM_CX)
+        xor %eax,%eax
         EXIT
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
         ENTER
-        movl TI_addr_limit(%ebx),%ebx
-        subl $1,%ebx
-        cmpl %ebx,%ecx
+        mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+        sub $1,%_ASM_BX
+        cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
-2:      movw %ax,(%ecx)
-        xorl %eax,%eax
+2:      movw %ax,(%_ASM_CX)
+        xor %eax,%eax
         EXIT
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
         ENTER
-        movl TI_addr_limit(%ebx),%ebx
-        subl $3,%ebx
-        cmpl %ebx,%ecx
+        mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+        sub $3,%_ASM_BX
+        cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
-3:      movl %eax,(%ecx)
-        xorl %eax,%eax
+3:      movl %eax,(%_ASM_CX)
+        xor %eax,%eax
         EXIT
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
         ENTER
-        movl TI_addr_limit(%ebx),%ebx
-        subl $7,%ebx
-        cmpl %ebx,%ecx
+        mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+        sub $7,%_ASM_BX
+        cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
-4:      movl %eax,(%ecx)
-5:      movl %edx,4(%ecx)
-        xorl %eax,%eax
+4:      mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+5:      movl %edx,4(%_ASM_CX)
+#endif
+        xor %eax,%eax
         EXIT
 ENDPROC(__put_user_8)
 
 bad_put_user:
-        CFI_STARTPROC simple
-        CFI_DEF_CFA esp, 2*4
-        CFI_OFFSET eip, -1*4
-        CFI_OFFSET ebx, -2*4
-        movl $-14,%eax
+        CFI_STARTPROC
+        movl $-EFAULT,%eax
         EXIT
 END(bad_put_user)
 
 .section __ex_table,"a"
-        .long 1b,bad_put_user
-        .long 2b,bad_put_user
-        .long 3b,bad_put_user
-        .long 4b,bad_put_user
-        .long 5b,bad_put_user
+        _ASM_PTR 1b,bad_put_user
+        _ASM_PTR 2b,bad_put_user
+        _ASM_PTR 3b,bad_put_user
+        _ASM_PTR 4b,bad_put_user
+#ifdef CONFIG_X86_32
+        _ASM_PTR 5b,bad_put_user
+#endif
 .previous
diff --git a/arch/x86/lib/putuser_64.S b/arch/x86/lib/putuser_64.S
deleted file mode 100644
index 4989f5a8fa9b..000000000000
--- a/arch/x86/lib/putuser_64.S
+++ /dev/null
@@ -1,106 +0,0 @@
-/*
- * __put_user functions.
- *
- * (C) Copyright 1998 Linus Torvalds
- * (C) Copyright 2005 Andi Kleen
- *
- * These functions have a non-standard call interface
- * to make them more efficient, especially as they
- * return an error value in addition to the "real"
- * return value.
- */
-
-/*
- * __put_user_X
- *
- * Inputs:      %rcx contains the address
- *              %rdx contains new value
- *
- * Outputs:     %rax is error code (0 or -EFAULT)
- *
- * %r8 is destroyed.
- *
- * These functions should not modify any other registers,
- * as they get called from within inline assembly.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/page.h>
-#include <asm/errno.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-        .text
-ENTRY(__put_user_1)
-        CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae bad_put_user
-1:      movb %dl,(%rcx)
-        xorl %eax,%eax
-        ret
-        CFI_ENDPROC
-ENDPROC(__put_user_1)
-
-ENTRY(__put_user_2)
-        CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $1,%rcx
-        jc 20f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae 20f
-        decq %rcx
-2:      movw %dx,(%rcx)
-        xorl %eax,%eax
-        ret
-20:     decq %rcx
-        jmp bad_put_user
-        CFI_ENDPROC
-ENDPROC(__put_user_2)
-
-ENTRY(__put_user_4)
-        CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $3,%rcx
-        jc 30f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae 30f
-        subq $3,%rcx
-3:      movl %edx,(%rcx)
-        xorl %eax,%eax
-        ret
-30:     subq $3,%rcx
-        jmp bad_put_user
-        CFI_ENDPROC
-ENDPROC(__put_user_4)
-
-ENTRY(__put_user_8)
-        CFI_STARTPROC
-        GET_THREAD_INFO(%r8)
-        addq $7,%rcx
-        jc 40f
-        cmpq threadinfo_addr_limit(%r8),%rcx
-        jae 40f
-        subq $7,%rcx
-4:      movq %rdx,(%rcx)
-        xorl %eax,%eax
-        ret
-40:     subq $7,%rcx
-        jmp bad_put_user
-        CFI_ENDPROC
-ENDPROC(__put_user_8)
-
-bad_put_user:
-        CFI_STARTPROC
-        movq $(-EFAULT),%rax
-        ret
-        CFI_ENDPROC
-END(bad_put_user)
-
-.section __ex_table,"a"
-        .quad 1b,bad_put_user
-        .quad 2b,bad_put_user
-        .quad 3b,bad_put_user
-        .quad 4b,bad_put_user
-.previous