Merge branch 'linus' into cpus4096

Conflicts:

	arch/x86/xen/smp.c
	kernel/sched_rt.c
	net/iucv/iucv.c

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

13 files changed, 469 insertions, 812 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 76f60f52a88..aa3fa411942 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -4,8 +4,9 @@
 
 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 += thunk_$(BITS).o
+lib-y += usercopy_$(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 ee1c3f63515..dfdf428975c 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -1,8 +1,10 @@
-/* Copyright 2002 Andi Kleen, SuSE Labs.
+/*
+ * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
+ * Copyright 2002 Andi Kleen, SuSE Labs.
  * Subject to the GNU Public License v2.
- * 
- * Functions to copy from and to user space.		
- */		 
+ *
+ * Functions to copy from and to user space.
+ */
 
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
@@ -20,60 +22,88 @@
 	.long \orig-1f	/* by default jump to orig */
 1:
 	.section .altinstr_replacement,"ax"
-2:	.byte 0xe9	             /* near jump with 32bit immediate */
+2:	.byte 0xe9			/* near jump with 32bit immediate */
 	.long \alt-1b /* offset */   /* or alternatively to alt */
 	.previous
 	.section .altinstructions,"a"
 	.align 8
 	.quad  0b
 	.quad  2b
-	.byte  \feature		     /* when feature is set */
+	.byte  \feature			/* when feature is set */
 	.byte  5
 	.byte  5
 	.previous
 	.endm
 
-/* Standard copy_to_user with segment limit checking */		
+	.macro ALIGN_DESTINATION
+#ifdef FIX_ALIGNMENT
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %r8d,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	.section __ex_table,"a"
+	.align 8
+	.quad 100b,103b
+	.quad 101b,103b
+	.previous
+#endif
+	.endm
+
+/* Standard copy_to_user with segment limit checking */
 ENTRY(copy_to_user)
 	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rdi,%rcx
 	addq %rdx,%rcx
-	jc  bad_to_user
-	cmpq threadinfo_addr_limit(%rax),%rcx
+	jc bad_to_user
+	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
 	CFI_ENDPROC
 
-ENTRY(copy_user_generic)
+/* Standard copy_from_user with segment limit checking */
+ENTRY(copy_from_user)
 	CFI_STARTPROC
-	movl $1,%ecx	/* set zero flag */
+	GET_THREAD_INFO(%rax)
+	movq %rsi,%rcx
+	addq %rdx,%rcx
+	jc bad_from_user
+	cmpq TI_addr_limit(%rax),%rcx
+	jae bad_from_user
 	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
 	CFI_ENDPROC
+ENDPROC(copy_from_user)
 
-ENTRY(__copy_from_user_inatomic)
+ENTRY(copy_user_generic)
 	CFI_STARTPROC
-	xorl %ecx,%ecx	/* clear zero flag */
 	ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
 	CFI_ENDPROC
+ENDPROC(copy_user_generic)
 
-/* Standard copy_from_user with segment limit checking */	
-ENTRY(copy_from_user)
+ENTRY(__copy_from_user_inatomic)
 	CFI_STARTPROC
-	GET_THREAD_INFO(%rax)
-	movq %rsi,%rcx
-	addq %rdx,%rcx
-	jc  bad_from_user
-	cmpq threadinfo_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
 	CFI_ENDPROC
-ENDPROC(copy_from_user)
-	
+ENDPROC(__copy_from_user_inatomic)
+
 	.section .fixup,"ax"
 	/* must zero dest */
+ENTRY(bad_from_user)
 bad_from_user:
 	CFI_STARTPROC
 	movl %edx,%ecx
@@ -81,271 +111,158 @@ bad_from_user:
 	rep
 	stosb
 bad_to_user:
-	movl	%edx,%eax
+	movl %edx,%eax
 	ret
 	CFI_ENDPROC
-END(bad_from_user)
+ENDPROC(bad_from_user)
 	.previous
-	
-		
+
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
- * This version is for CPUs like P4 that don't have efficient micro code for rep movsq
- * 	
- * Input:	
+ * This version is for CPUs like P4 that don't have efficient micro
+ * code for rep movsq
+ *
+ * Input:
  * rdi destination
  * rsi source
  * rdx count
- * ecx zero flag -- if true zero destination on error
  *
- * Output:		
- * eax uncopied bytes or 0 if successful.
+ * Output:
+ * eax uncopied bytes or 0 if successfull.
  */
 ENTRY(copy_user_generic_unrolled)
 	CFI_STARTPROC
-	pushq %rbx
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rbx, 0
-	pushq %rcx
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rcx, 0
-	xorl %eax,%eax		/*zero for the exception handler */
-
-#ifdef FIX_ALIGNMENT
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jnz  .Lbad_alignment
-.Lafter_bad_alignment:
-#endif
-
-	movq %rdx,%rcx
-
-	movl $64,%ebx
-	shrq $6,%rdx
-	decq %rdx
-	js   .Lhandle_tail
-
-	.p2align 4
-.Lloop:
-.Ls1:	movq (%rsi),%r11
-.Ls2:	movq 1*8(%rsi),%r8
-.Ls3:	movq 2*8(%rsi),%r9
-.Ls4:	movq 3*8(%rsi),%r10
-.Ld1:	movq %r11,(%rdi)
-.Ld2:	movq %r8,1*8(%rdi)
-.Ld3:	movq %r9,2*8(%rdi)
-.Ld4:	movq %r10,3*8(%rdi)
-
-.Ls5:	movq 4*8(%rsi),%r11
-.Ls6:	movq 5*8(%rsi),%r8
-.Ls7:	movq 6*8(%rsi),%r9
-.Ls8:	movq 7*8(%rsi),%r10
-.Ld5:	movq %r11,4*8(%rdi)
-.Ld6:	movq %r8,5*8(%rdi)
-.Ld7:	movq %r9,6*8(%rdi)
-.Ld8:	movq %r10,7*8(%rdi)
-
-	decq %rdx
-
+	cmpl $8,%edx
+	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	ALIGN_DESTINATION
+	movl %edx,%ecx
+	andl $63,%edx
+	shrl $6,%ecx
+	jz 17f
+1:	movq (%rsi),%r8
+2:	movq 1*8(%rsi),%r9
+3:	movq 2*8(%rsi),%r10
+4:	movq 3*8(%rsi),%r11
+5:	movq %r8,(%rdi)
+6:	movq %r9,1*8(%rdi)
+7:	movq %r10,2*8(%rdi)
+8:	movq %r11,3*8(%rdi)
+9:	movq 4*8(%rsi),%r8
+10:	movq 5*8(%rsi),%r9
+11:	movq 6*8(%rsi),%r10
+12:	movq 7*8(%rsi),%r11
+13:	movq %r8,4*8(%rdi)
+14:	movq %r9,5*8(%rdi)
+15:	movq %r10,6*8(%rdi)
+16:	movq %r11,7*8(%rdi)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
-
-	jns  .Lloop
-
-	.p2align 4
-.Lhandle_tail:
-	movl %ecx,%edx
-	andl $63,%ecx
-	shrl $3,%ecx
-	jz   .Lhandle_7
-	movl $8,%ebx
-	.p2align 4
-.Lloop_8:
-.Ls9:	movq (%rsi),%r8
-.Ld9:	movq %r8,(%rdi)
 	decl %ecx
-	leaq 8(%rdi),%rdi
+	jnz 1b
+17:	movl %edx,%ecx
+	andl $7,%edx
+	shrl $3,%ecx
+	jz 20f
+18:	movq (%rsi),%r8
+19:	movq %r8,(%rdi)
 	leaq 8(%rsi),%rsi
-	jnz .Lloop_8
-
-.Lhandle_7:
+	leaq 8(%rdi),%rdi
+	decl %ecx
+	jnz 18b
+20:	andl %edx,%edx
+	jz 23f
 	movl %edx,%ecx
-	andl $7,%ecx
-	jz   .Lende
-	.p2align 4
-.Lloop_1:
-.Ls10:	movb (%rsi),%bl
-.Ld10:	movb %bl,(%rdi)
-	incq %rdi
+21:	movb (%rsi),%al
+22:	movb %al,(%rdi)
 	incq %rsi
+	incq %rdi
 	decl %ecx
-	jnz .Lloop_1
-
-	CFI_REMEMBER_STATE
-.Lende:
-	popq %rcx
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE rcx
-	popq %rbx
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE rbx
+	jnz 21b
+23:	xor %eax,%eax
 	ret
-	CFI_RESTORE_STATE
 
-#ifdef FIX_ALIGNMENT
-	/* align destination */
-	.p2align 4
-.Lbad_alignment:
-	movl $8,%r9d
-	subl %ecx,%r9d
-	movl %r9d,%ecx
-	cmpq %r9,%rdx
-	jz   .Lhandle_7
-	js   .Lhandle_7
-.Lalign_1:
-.Ls11:	movb (%rsi),%bl
-.Ld11:	movb %bl,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .Lalign_1
-	subq %r9,%rdx
-	jmp .Lafter_bad_alignment
-#endif
+	.section .fixup,"ax"
+30:	shll $6,%ecx
+	addl %ecx,%edx
+	jmp 60f
+40:	lea (%rdx,%rcx,8),%rdx
+	jmp 60f
+50:	movl %ecx,%edx
+60:	jmp copy_user_handle_tail /* ecx is zerorest also */
+	.previous
 
-	/* table sorted by exception address */
 	.section __ex_table,"a"
 	.align 8
-	.quad .Ls1,.Ls1e	/* Ls1-Ls4 have copied zero bytes */
-	.quad .Ls2,.Ls1e
-	.quad .Ls3,.Ls1e
-	.quad .Ls4,.Ls1e
-	.quad .Ld1,.Ls1e	/* Ld1-Ld4 have copied 0-24 bytes */
-	.quad .Ld2,.Ls2e
-	.quad .Ld3,.Ls3e
-	.quad .Ld4,.Ls4e
-	.quad .Ls5,.Ls5e	/* Ls5-Ls8 have copied 32 bytes */
-	.quad .Ls6,.Ls5e
-	.quad .Ls7,.Ls5e
-	.quad .Ls8,.Ls5e
-	.quad .Ld5,.Ls5e	/* Ld5-Ld8 have copied 32-56 bytes */
-	.quad .Ld6,.Ls6e
-	.quad .Ld7,.Ls7e
-	.quad .Ld8,.Ls8e
-	.quad .Ls9,.Le_quad
-	.quad .Ld9,.Le_quad
-	.quad .Ls10,.Le_byte
-	.quad .Ld10,.Le_byte
-#ifdef FIX_ALIGNMENT
-	.quad .Ls11,.Lzero_rest
-	.quad .Ld11,.Lzero_rest
-#endif
-	.quad .Le5,.Le_zero
+	.quad 1b,30b
+	.quad 2b,30b
+	.quad 3b,30b
+	.quad 4b,30b
+	.quad 5b,30b
+	.quad 6b,30b
+	.quad 7b,30b
+	.quad 8b,30b
+	.quad 9b,30b
+	.quad 10b,30b
+	.quad 11b,30b
+	.quad 12b,30b
+	.quad 13b,30b
+	.quad 14b,30b
+	.quad 15b,30b
+	.quad 16b,30b
+	.quad 18b,40b
+	.quad 19b,40b
+	.quad 21b,50b
+	.quad 22b,50b
 	.previous
-
-	/* eax: zero, ebx: 64 */
-.Ls1e: 	addl $8,%eax		/* eax is bytes left uncopied within the loop (Ls1e: 64 .. Ls8e: 8) */
-.Ls2e: 	addl $8,%eax
-.Ls3e: 	addl $8,%eax
-.Ls4e: 	addl $8,%eax
-.Ls5e: 	addl $8,%eax
-.Ls6e: 	addl $8,%eax
-.Ls7e: 	addl $8,%eax
-.Ls8e: 	addl $8,%eax
-	addq %rbx,%rdi	/* +64 */
-	subq %rax,%rdi  /* correct destination with computed offset */
-
-	shlq $6,%rdx	/* loop counter * 64 (stride length) */
-	addq %rax,%rdx	/* add offset to loopcnt */
-	andl $63,%ecx	/* remaining bytes */
-	addq %rcx,%rdx	/* add them */
-	jmp .Lzero_rest
-
-	/* exception on quad word loop in tail handling */
-	/* ecx:	loopcnt/8, %edx: length, rdi: correct */
-.Le_quad:
-	shll $3,%ecx
-	andl $7,%edx
-	addl %ecx,%edx
-	/* edx: bytes to zero, rdi: dest, eax:zero */
-.Lzero_rest:
-	cmpl $0,(%rsp)
-	jz   .Le_zero
-	movq %rdx,%rcx
-.Le_byte:
-	xorl %eax,%eax
-.Le5:	rep
-	stosb
-	/* when there is another exception while zeroing the rest just return */
-.Le_zero:
-	movq %rdx,%rax
-	jmp .Lende
 	CFI_ENDPROC
-ENDPROC(copy_user_generic)
+ENDPROC(copy_user_generic_unrolled)
 
-
-	/* Some CPUs run faster using the string copy instructions.
-	   This is also a lot simpler. Use them when possible.
-	   Patch in jmps to this code instead of copying it fully
-	   to avoid unwanted aliasing in the exception tables. */
-
- /* rdi	destination
-  * rsi source
-  * rdx count
-  * ecx zero flag
-  *
-  * Output:
-  * eax uncopied bytes or 0 if successfull.
-  *
-  * Only 4GB of copy is supported. This shouldn't be a problem
-  * because the kernel normally only writes from/to page sized chunks
-  * even if user space passed a longer buffer.
-  * And more would be dangerous because both Intel and AMD have
-  * errata with rep movsq > 4GB. If someone feels the need to fix
-  * this please consider this.
-  */
+/* Some CPUs run faster using the string copy instructions.
+ * This is also a lot simpler. Use them when possible.
+ *
+ * Only 4GB of copy is supported. This shouldn't be a problem
+ * because the kernel normally only writes from/to page sized chunks
+ * even if user space passed a longer buffer.
+ * And more would be dangerous because both Intel and AMD have
+ * errata with rep movsq > 4GB. If someone feels the need to fix
+ * this please consider this.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
 ENTRY(copy_user_generic_string)
 	CFI_STARTPROC
-	movl %ecx,%r8d		/* save zero flag */
+	andl %edx,%edx
+	jz 4f
+	cmpl $8,%edx
+	jb 2f		/* less than 8 bytes, go to byte copy loop */
+	ALIGN_DESTINATION
 	movl %edx,%ecx
 	shrl $3,%ecx
-	andl $7,%edx	
-	jz   10f
-1:	rep 
-	movsq 
-	movl %edx,%ecx
-2:	rep
-	movsb
-9:	movl %ecx,%eax
-	ret
-
-	/* multiple of 8 byte */
-10:	rep
+	andl $7,%edx
+1:	rep
 	movsq
-	xor %eax,%eax
+2:	movl %edx,%ecx
+3:	rep
+	movsb
+4:	xorl %eax,%eax
 	ret
 
-	/* exception handling */
-3:      lea (%rdx,%rcx,8),%rax	/* exception on quad loop */
-	jmp 6f
-5:	movl %ecx,%eax		/* exception on byte loop */
-	/* eax: left over bytes */
-6:	testl %r8d,%r8d		/* zero flag set? */
-	jz 7f
-	movl %eax,%ecx		/* initialize x86 loop counter */
-	push %rax
-	xorl %eax,%eax
-8:	rep
-	stosb 			/* zero the rest */
-11:	pop %rax
-7:	ret
-	CFI_ENDPROC
-END(copy_user_generic_c)
+	.section .fixup,"ax"
+11:	lea (%rdx,%rcx,8),%rcx
+12:	movl %ecx,%edx		/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
 
 	.section __ex_table,"a"
-	.quad 1b,3b
-	.quad 2b,5b
-	.quad 8b,11b
-	.quad 10b,3b
+	.align 8
+	.quad 1b,11b
+	.quad 3b,12b
 	.previous
+	CFI_ENDPROC
+ENDPROC(copy_user_generic_string)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index 9d3d1ab8376..40e0e309d27 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -1,4 +1,6 @@
-/* Copyright 2002 Andi Kleen, SuSE Labs.
+/*
+ * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
+ * Copyright 2002 Andi Kleen, SuSE Labs.
  * Subject to the GNU Public License v2.
  *
  * Functions to copy from and to user space.
@@ -12,204 +14,125 @@
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
-#include <asm/cpufeature.h>
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- *
- * Input:
- * rdi destination
- * rsi source
- * rdx count
- * rcx zero flag	when 1 zero on exception
- *
- * Output:
- * eax uncopied bytes or 0 if successful.
- */
-ENTRY(__copy_user_nocache)
-	CFI_STARTPROC
-	pushq %rbx
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rbx, 0
-	pushq %rcx		/* save zero flag */
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rcx, 0
-
-	xorl %eax,%eax		/* zero for the exception handler */
 
+	.macro ALIGN_DESTINATION
 #ifdef FIX_ALIGNMENT
 	/* check for bad alignment of destination */
 	movl %edi,%ecx
 	andl $7,%ecx
-	jnz  .Lbad_alignment
-.Lafter_bad_alignment:
-#endif
-
-	movq %rdx,%rcx
-
-	movl $64,%ebx
-	shrq $6,%rdx
-	decq %rdx
-	js   .Lhandle_tail
-
-	.p2align 4
-.Lloop:
-.Ls1:	movq (%rsi),%r11
-.Ls2:	movq 1*8(%rsi),%r8
-.Ls3:	movq 2*8(%rsi),%r9
-.Ls4:	movq 3*8(%rsi),%r10
-.Ld1:	movnti %r11,(%rdi)
-.Ld2:	movnti %r8,1*8(%rdi)
-.Ld3:	movnti %r9,2*8(%rdi)
-.Ld4:	movnti %r10,3*8(%rdi)
-
-.Ls5:	movq 4*8(%rsi),%r11
-.Ls6:	movq 5*8(%rsi),%r8
-.Ls7:	movq 6*8(%rsi),%r9
-.Ls8:	movq 7*8(%rsi),%r10
-.Ld5:	movnti %r11,4*8(%rdi)
-.Ld6:	movnti %r8,5*8(%rdi)
-.Ld7:	movnti %r9,6*8(%rdi)
-.Ld8:	movnti %r10,7*8(%rdi)
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %r8d,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
 
-	dec  %rdx
+	.section __ex_table,"a"
+	.align 8
+	.quad 100b,103b
+	.quad 101b,103b
+	.previous
+#endif
+	.endm
 
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+	CFI_STARTPROC
+	cmpl $8,%edx
+	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	ALIGN_DESTINATION
+	movl %edx,%ecx
+	andl $63,%edx
+	shrl $6,%ecx
+	jz 17f
+1:	movq (%rsi),%r8
+2:	movq 1*8(%rsi),%r9
+3:	movq 2*8(%rsi),%r10
+4:	movq 3*8(%rsi),%r11
+5:	movnti %r8,(%rdi)
+6:	movnti %r9,1*8(%rdi)
+7:	movnti %r10,2*8(%rdi)
+8:	movnti %r11,3*8(%rdi)
+9:	movq 4*8(%rsi),%r8
+10:	movq 5*8(%rsi),%r9
+11:	movq 6*8(%rsi),%r10
+12:	movq 7*8(%rsi),%r11
+13:	movnti %r8,4*8(%rdi)
+14:	movnti %r9,5*8(%rdi)
+15:	movnti %r10,6*8(%rdi)
+16:	movnti %r11,7*8(%rdi)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
-
-	jns  .Lloop
-
-	.p2align 4
-.Lhandle_tail:
-	movl %ecx,%edx
-	andl $63,%ecx
-	shrl $3,%ecx
-	jz   .Lhandle_7
-	movl $8,%ebx
-	.p2align 4
-.Lloop_8:
-.Ls9:	movq (%rsi),%r8
-.Ld9:	movnti %r8,(%rdi)
 	decl %ecx
-	leaq 8(%rdi),%rdi
+	jnz 1b
+17:	movl %edx,%ecx
+	andl $7,%edx
+	shrl $3,%ecx
+	jz 20f
+18:	movq (%rsi),%r8
+19:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
-	jnz .Lloop_8
-
-.Lhandle_7:
+	leaq 8(%rdi),%rdi
+	decl %ecx
+	jnz 18b
+20:	andl %edx,%edx
+	jz 23f
 	movl %edx,%ecx
-	andl $7,%ecx
-	jz   .Lende
-	.p2align 4
-.Lloop_1:
-.Ls10:	movb (%rsi),%bl
-.Ld10:	movb %bl,(%rdi)
-	incq %rdi
+21:	movb (%rsi),%al
+22:	movb %al,(%rdi)
 	incq %rsi
+	incq %rdi
 	decl %ecx
-	jnz .Lloop_1
-
-	CFI_REMEMBER_STATE
-.Lende:
-	popq %rcx
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE %rcx
-	popq %rbx
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE rbx
+	jnz 21b
+23:	xorl %eax,%eax
 	sfence
 	ret
-	CFI_RESTORE_STATE
 
-#ifdef FIX_ALIGNMENT
-	/* align destination */
-	.p2align 4
-.Lbad_alignment:
-	movl $8,%r9d
-	subl %ecx,%r9d
-	movl %r9d,%ecx
-	cmpq %r9,%rdx
-	jz   .Lhandle_7
-	js   .Lhandle_7
-.Lalign_1:
-.Ls11:	movb (%rsi),%bl
-.Ld11:	movb %bl,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .Lalign_1
-	subq %r9,%rdx
-	jmp .Lafter_bad_alignment
-#endif
+	.section .fixup,"ax"
+30:	shll $6,%ecx
+	addl %ecx,%edx
+	jmp 60f
+40:	lea (%rdx,%rcx,8),%rdx
+	jmp 60f
+50:	movl %ecx,%edx
+60:	sfence
+	movl %r8d,%ecx
+	jmp copy_user_handle_tail
+	.previous
 
-	/* table sorted by exception address */
 	.section __ex_table,"a"
-	.align 8
-	.quad .Ls1,.Ls1e	/* .Ls[1-4] - 0 bytes copied */
-	.quad .Ls2,.Ls1e
-	.quad .Ls3,.Ls1e
-	.quad .Ls4,.Ls1e
-	.quad .Ld1,.Ls1e	/* .Ld[1-4] - 0..24 bytes coped */
-	.quad .Ld2,.Ls2e
-	.quad .Ld3,.Ls3e
-	.quad .Ld4,.Ls4e
-	.quad .Ls5,.Ls5e	/* .Ls[5-8] - 32 bytes copied */
-	.quad .Ls6,.Ls5e
-	.quad .Ls7,.Ls5e
-	.quad .Ls8,.Ls5e
-	.quad .Ld5,.Ls5e	/* .Ld[5-8] - 32..56 bytes copied */
-	.quad .Ld6,.Ls6e
-	.quad .Ld7,.Ls7e
-	.quad .Ld8,.Ls8e
-	.quad .Ls9,.Le_quad
-	.quad .Ld9,.Le_quad
-	.quad .Ls10,.Le_byte
-	.quad .Ld10,.Le_byte
-#ifdef FIX_ALIGNMENT
-	.quad .Ls11,.Lzero_rest
-	.quad .Ld11,.Lzero_rest
-#endif
-	.quad .Le5,.Le_zero
+	.quad 1b,30b
+	.quad 2b,30b
+	.quad 3b,30b
+	.quad 4b,30b
+	.quad 5b,30b
+	.quad 6b,30b
+	.quad 7b,30b
+	.quad 8b,30b
+	.quad 9b,30b
+	.quad 10b,30b
+	.quad 11b,30b
+	.quad 12b,30b
+	.quad 13b,30b
+	.quad 14b,30b
+	.quad 15b,30b
+	.quad 16b,30b
+	.quad 18b,40b
+	.quad 19b,40b
+	.quad 21b,50b
+	.quad 22b,50b
 	.previous
-
-	/* eax: zero, ebx: 64 */
-.Ls1e: 	addl $8,%eax	/* eax: bytes left uncopied: Ls1e: 64 .. Ls8e: 8 */
-.Ls2e: 	addl $8,%eax
-.Ls3e: 	addl $8,%eax
-.Ls4e: 	addl $8,%eax
-.Ls5e: 	addl $8,%eax
-.Ls6e: 	addl $8,%eax
-.Ls7e: 	addl $8,%eax
-.Ls8e: 	addl $8,%eax
-	addq %rbx,%rdi	/* +64 */
-	subq %rax,%rdi  /* correct destination with computed offset */
-
-	shlq $6,%rdx	/* loop counter * 64 (stride length) */
-	addq %rax,%rdx	/* add offset to loopcnt */
-	andl $63,%ecx	/* remaining bytes */
-	addq %rcx,%rdx	/* add them */
-	jmp .Lzero_rest
-
-	/* exception on quad word loop in tail handling */
-	/* ecx:	loopcnt/8, %edx: length, rdi: correct */
-.Le_quad:
-	shll $3,%ecx
-	andl $7,%edx
-	addl %ecx,%edx
-	/* edx: bytes to zero, rdi: dest, eax:zero */
-.Lzero_rest:
-	cmpl $0,(%rsp)	/* zero flag set? */
-	jz   .Le_zero
-	movq %rdx,%rcx
-.Le_byte:
-	xorl %eax,%eax
-.Le5:	rep
-	stosb
-	/* when there is another exception while zeroing the rest just return */
-.Le_zero:
-	movq %rdx,%rax
-	jmp .Lende
 	CFI_ENDPROC
 ENDPROC(__copy_user_nocache)
-
-
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay.c
index d710f2d167b..f4568605d7d 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay.c
@@ -3,6 +3,7 @@
  *
  *	Copyright (C) 1993 Linus Torvalds
  *	Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *	Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
  *
  *	The __delay function must _NOT_ be inlined as its execution time
  *	depends wildly on alignment on many x86 processors. The additional
@@ -28,16 +29,22 @@
 /* simple loop based delay: */
 static void delay_loop(unsigned long loops)
 {
-	int d0;
-
-	__asm__ __volatile__(
-		"\tjmp 1f\n"
-		".align 16\n"
-		"1:\tjmp 2f\n"
-		".align 16\n"
-		"2:\tdecl %0\n\tjns 2b"
-		:"=&a" (d0)
-		:"0" (loops));
+	asm volatile(
+		"	test %0,%0	\n"
+		"	jz 3f		\n"
+		"	jmp 1f		\n"
+
+		".align 16		\n"
+		"1:	jmp 2f		\n"
+
+		".align 16		\n"
+		"2:	dec %0		\n"
+		"	jnz 2b		\n"
+		"3:	dec %0		\n"
+
+		: /* we don't need output */
+		:"a" (loops)
+	);
 }
 
 /* TSC based delay: */
@@ -91,7 +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;
@@ -101,31 +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 4c441be9264..00000000000
--- 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 5448876261f..ad374003742 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 6d84b53f12a..00000000000
--- 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/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
index 57d043fa893..d5a2b39f882 100644
--- a/arch/x86/lib/msr-on-cpu.c
+++ b/arch/x86/lib/msr-on-cpu.c
@@ -30,10 +30,10 @@ static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
 
 	rv.msr_no = msr_no;
 	if (safe) {
-		smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
 		err = rv.err;
 	} else {
-		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
 	}
 	*l = rv.l;
 	*h = rv.h;
@@ -64,10 +64,10 @@ static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
 	rv.l = l;
 	rv.h = h;
 	if (safe) {
-		smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
 		err = rv.err;
 	} else {
-		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
 	}
 
 	return err;
diff --git a/arch/x86/lib/putuser_32.S b/arch/x86/lib/putuser.S
index f58fba109d1..36b0d15ae6e 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 4989f5a8fa9..00000000000
--- 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
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
new file mode 100644
index 00000000000..650b11e00ec
--- /dev/null
+++ b/arch/x86/lib/thunk_32.S
@@ -0,0 +1,47 @@
+/*
+ * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
+ * Copyright 2008 by Steven Rostedt, Red Hat, Inc
+ *  (inspired by Andi Kleen's thunk_64.S)
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+
+	#include <linux/linkage.h>
+
+#define ARCH_TRACE_IRQS_ON			\
+	pushl %eax;				\
+	pushl %ecx;				\
+	pushl %edx;				\
+	call trace_hardirqs_on;			\
+	popl %edx;				\
+	popl %ecx;				\
+	popl %eax;
+
+#define ARCH_TRACE_IRQS_OFF			\
+	pushl %eax;				\
+	pushl %ecx;				\
+	pushl %edx;				\
+	call trace_hardirqs_off;		\
+	popl %edx;				\
+	popl %ecx;				\
+	popl %eax;
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* put return address in eax (arg1) */
+	.macro thunk_ra name,func
+	.globl \name
+\name:
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	/* Place EIP in the arg1 */
+	movl 3*4(%esp), %eax
+	call \func
+	popl %edx
+	popl %ecx
+	popl %eax
+	ret
+	.endm
+
+	thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+	thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#endif
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index e009251d4e9..bf9a7d5a542 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -2,6 +2,7 @@
  * Save registers before calling assembly functions. This avoids
  * disturbance of register allocation in some inline assembly constructs.
  * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
+ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
 
@@ -42,8 +43,22 @@
 #endif	
 	
 #ifdef CONFIG_TRACE_IRQFLAGS
-	thunk trace_hardirqs_on_thunk,trace_hardirqs_on
-	thunk trace_hardirqs_off_thunk,trace_hardirqs_off
+	/* put return address in rdi (arg1) */
+	.macro thunk_ra name,func
+	.globl \name
+\name:
+	CFI_STARTPROC
+	SAVE_ARGS
+	/* SAVE_ARGS pushs 9 elements */
+	/* the next element would be the rip */
+	movq 9*8(%rsp), %rdi
+	call \func
+	jmp  restore
+	CFI_ENDPROC
+	.endm
+
+	thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+	thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 0c89d1bb028..f4df6e7c718 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -158,3 +158,26 @@ unsigned long copy_in_user(void __user *to, const void __user *from, unsigned le
 }
 EXPORT_SYMBOL(copy_in_user);
 
+/*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ */
+unsigned long
+copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
+{
+	char c;
+	unsigned zero_len;
+
+	for (; len; --len) {
+		if (__get_user_nocheck(c, from++, sizeof(char)))
+			break;
+		if (__put_user_nocheck(c, to++, sizeof(char)))
+			break;
+	}
+
+	for (c = 0, zero_len = len; zerorest && zero_len; --zero_len)
+		if (__put_user_nocheck(c, to++, sizeof(char)))
+			break;
+	return len;
+}