Merge branches 'fixes' and 'ioremap' into for-linus

23 files changed, 184 insertions, 516 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1530afb07c85..f2587888d987 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,7 +17,6 @@ clean-files := inat-tables.c
 obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 
 lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
@@ -40,6 +39,6 @@ else
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
-        lib-y += copy_user_64.o copy_user_nocache_64.o
+        lib-y += copy_user_64.o
 	lib-y += cmpxchg16b_emu.o
 endif
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 00933d5e992f..9b0ca8fe80fc 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -11,26 +11,23 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
-	pushfl_cfi
+	pushfl
 	cli
 .endm
 
 .macro UNLOCK reg
-	popfl_cfi
+	popfl
 .endm
 
 #define BEGIN(op) \
 .macro endp; \
-	CFI_ENDPROC; \
 ENDPROC(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
 ENTRY(atomic64_##op##_386); \
-	CFI_STARTPROC; \
 	LOCK v;
 
 #define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 082a85167a5b..db3ae85440ff 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -11,7 +11,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 .macro read64 reg
 	movl %ebx, %eax
@@ -22,16 +21,11 @@
 .endm
 
 ENTRY(atomic64_read_cx8)
-	CFI_STARTPROC
-
 	read64 %ecx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_read_cx8)
 
 ENTRY(atomic64_set_cx8)
-	CFI_STARTPROC
-
 1:
 /* we don't need LOCK_PREFIX since aligned 64-bit writes
  * are atomic on 586 and newer */
@@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_set_cx8)
 
 ENTRY(atomic64_xchg_cx8)
-	CFI_STARTPROC
-
 1:
 	LOCK_PREFIX
 	cmpxchg8b (%esi)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
+	pushl %ebp
+	pushl %ebx
+	pushl %esi
+	pushl %edi
 
 	movl %eax, %esi
 	movl %edx, %edi
@@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %edi
+	popl %esi
+	popl %ebx
+	popl %ebp
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -93,8 +81,7 @@ addsub_return sub sub sbb
 
 .macro incdec_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -119,8 +105,7 @@ incdec_return inc add adc
 incdec_return dec sub sbb
 
 ENTRY(atomic64_dec_if_positive_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8)
 2:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_dec_if_positive_cx8)
 
 ENTRY(atomic64_add_unless_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
+	pushl %ebp
+	pushl %ebx
 /* these just push these two parameters on the stack */
-	pushl_cfi_reg edi
-	pushl_cfi_reg ecx
+	pushl %edi
+	pushl %ecx
 
 	movl %eax, %ebp
 	movl %edx, %edi
@@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8)
 	movl $1, %eax
 3:
 	addl $8, %esp
-	CFI_ADJUST_CFA_OFFSET -8
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %ebx
+	popl %ebp
 	ret
 4:
 	cmpl %edx, 4(%esp)
 	jne 2b
 	xorl %eax, %eax
 	jmp 3b
-	CFI_ENDPROC
 ENDPROC(atomic64_add_unless_cx8)
 
 ENTRY(atomic64_inc_not_zero_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8)
 
 	movl $1, %eax
 3:
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 9bc944a91274..c1e623209853 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 				
@@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * alignment for the unrolled loop.
 	   */		
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg: unsigned char *buff
@@ -129,10 +127,9 @@ ENTRY(csum_partial)
 	jz 8f
 	roll $8, %eax
 8:
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 
 #else
@@ -140,9 +137,8 @@ ENDPROC(csum_partial)
 /* Version for PentiumII/PPro */
 
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
@@ -249,10 +245,9 @@ ENTRY(csum_partial)
 	jz 90f
 	roll $8, %eax
 90: 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 				
 #endif
@@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 #define FP		12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	subl  $4,%esp	
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %edi
+	pushl %esi
+	pushl %ebx
 	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
 	movl ARGBASE+4(%esp),%esi	# src
@@ -401,12 +394,11 @@ DST(	movb %cl, (%edi)	)
 
 .previous
 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi %ecx			# equivalent to addl $4,%esp
+	popl %ebx
+	popl %esi
+	popl %edi
+	popl %ecx			# equivalent to addl $4,%esp
 	ret	
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 
 #else
@@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic)
 #define ARGBASE 12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
+	pushl %ebx
+	pushl %edi
+	pushl %esi
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
 	movl ARGBASE+12(%esp),%ecx	#len
@@ -489,11 +480,10 @@ DST(	movb %dl, (%edi)         )
 	jmp  7b			
 .previous				
 
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi_reg ebx
+	popl %esi
+	popl %edi
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 				
 #undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index e67e579c93bd..a2fe51b00cce 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,4 @@
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -15,7 +14,6 @@
  * %rdi	- page
  */
 ENTRY(clear_page)
-	CFI_STARTPROC
 
 	ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp clear_page_c_e", X86_FEATURE_ERMS
@@ -24,11 +22,9 @@ ENTRY(clear_page)
 	xorl %eax,%eax
 	rep stosq
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page)
 
 ENTRY(clear_page_orig)
-	CFI_STARTPROC
 
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
@@ -48,14 +44,11 @@ ENTRY(clear_page_orig)
 	jnz	.Lloop
 	nop
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_orig)
 
 ENTRY(clear_page_c_e)
-	CFI_STARTPROC
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_c_e)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 40a172541ee2..9b330242e740 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,7 +6,6 @@
  *
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/percpu.h>
 
 .text
@@ -21,7 +20,6 @@
  * %al  : Operation successful
  */
 ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -32,7 +30,7 @@ CFI_STARTPROC
 # *atomic* on a single cpu (as provided by the this_cpu_xx class of
 # macros).
 #
-	pushfq_cfi
+	pushfq
 	cli
 
 	cmpq PER_CPU_VAR((%rsi)), %rax
@@ -43,17 +41,13 @@ CFI_STARTPROC
 	movq %rbx, PER_CPU_VAR((%rsi))
 	movq %rcx, PER_CPU_VAR(8(%rsi))
 
-	CFI_REMEMBER_STATE
-	popfq_cfi
+	popfq
 	mov $1, %al
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
-	popfq_cfi
+	popfq
 	xor %al,%al
 	ret
 
-CFI_ENDPROC
-
 ENDPROC(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index b4807fce5177..ad5349778490 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 .text
 
@@ -20,14 +19,13 @@
  * %ecx : high 32 bits of new value
  */
 ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg8b (%esi)' on UP except we don't
 # set the whole ZF thing (caller will just compare
 # eax:edx with the expected value)
 #
-	pushfl_cfi
+	pushfl
 	cli
 
 	cmpl  (%esi), %eax
@@ -38,18 +36,15 @@ CFI_STARTPROC
 	movl %ebx,  (%esi)
 	movl %ecx, 4(%esi)
 
-	CFI_REMEMBER_STATE
-	popfl_cfi
+	popfl
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
 	movl  (%esi), %eax
 .Lhalf_same:
 	movl 4(%esi), %edx
 
-	popfl_cfi
+	popfl
 	ret
 
-CFI_ENDPROC
 ENDPROC(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 8239dbcbf984..009f98216b7e 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,6 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -13,22 +12,16 @@
  */
 	ALIGN
 ENTRY(copy_page)
-	CFI_STARTPROC
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page)
 
 ENTRY(copy_page_regs)
-	CFI_STARTPROC
 	subq	$2*8,	%rsp
-	CFI_ADJUST_CFA_OFFSET 2*8
 	movq	%rbx,	(%rsp)
-	CFI_REL_OFFSET rbx, 0
 	movq	%r12,	1*8(%rsp)
-	CFI_REL_OFFSET r12, 1*8
 
 	movl	$(4096/64)-5,	%ecx
 	.p2align 4
@@ -87,11 +80,7 @@ ENTRY(copy_page_regs)
 	jnz	.Loop2
 
 	movq	(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq	1*8(%rsp), %r12
-	CFI_RESTORE r12
 	addq	$2*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -2*8
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997dfaef24..982ce34f4a9b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
@@ -16,33 +15,8 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 
-	.macro ALIGN_DESTINATION
-	/* 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 %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-	.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
@@ -54,12 +28,10 @@ ENTRY(_copy_to_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_to_user)
 
 /* Standard copy_from_user with segment limit checking */
 ENTRY(_copy_from_user)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rsi,%rcx
 	addq %rdx,%rcx
@@ -71,14 +43,12 @@ ENTRY(_copy_from_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_from_user)
 
 	.section .fixup,"ax"
 	/* must zero dest */
 ENTRY(bad_from_user)
 bad_from_user:
-	CFI_STARTPROC
 	movl %edx,%ecx
 	xorl %eax,%eax
 	rep
@@ -86,7 +56,6 @@ bad_from_user:
 bad_to_user:
 	movl %edx,%eax
 	ret
-	CFI_ENDPROC
 ENDPROC(bad_from_user)
 	.previous
 
@@ -104,7 +73,6 @@ ENDPROC(bad_from_user)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_unrolled)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 20f		/* less then 8 bytes, go to byte copy loop */
@@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled)
 	_ASM_EXTABLE(19b,40b)
 	_ASM_EXTABLE(21b,50b)
 	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_unrolled)
 
 /* Some CPUs run faster using the string copy instructions.
@@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_string)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
@@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string)
 
 	_ASM_EXTABLE(1b,11b)
 	_ASM_EXTABLE(3b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
 
 /*
@@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_enhanced_fast_string)
-	CFI_STARTPROC
 	ASM_STAC
 	movl %edx,%ecx
 1:	rep
@@ -264,5 +228,94 @@ ENTRY(copy_user_enhanced_fast_string)
 	.previous
 
 	_ASM_EXTABLE(1b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+	ASM_STAC
+	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
+	decl %ecx
+	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
+	leaq 8(%rdi),%rdi
+	decl %ecx
+	jnz 18b
+20:	andl %edx,%edx
+	jz 23f
+	movl %edx,%ecx
+21:	movb (%rsi),%al
+22:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 21b
+23:	xorl %eax,%eax
+	ASM_CLAC
+	sfence
+	ret
+
+	.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
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE(1b,30b)
+	_ASM_EXTABLE(2b,30b)
+	_ASM_EXTABLE(3b,30b)
+	_ASM_EXTABLE(4b,30b)
+	_ASM_EXTABLE(5b,30b)
+	_ASM_EXTABLE(6b,30b)
+	_ASM_EXTABLE(7b,30b)
+	_ASM_EXTABLE(8b,30b)
+	_ASM_EXTABLE(9b,30b)
+	_ASM_EXTABLE(10b,30b)
+	_ASM_EXTABLE(11b,30b)
+	_ASM_EXTABLE(12b,30b)
+	_ASM_EXTABLE(13b,30b)
+	_ASM_EXTABLE(14b,30b)
+	_ASM_EXTABLE(15b,30b)
+	_ASM_EXTABLE(16b,30b)
+	_ASM_EXTABLE(18b,40b)
+	_ASM_EXTABLE(19b,40b)
+	_ASM_EXTABLE(21b,50b)
+	_ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
deleted file mode 100644
index 6a4f43c2d9e6..000000000000
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * 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.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-	.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 %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-#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
-	ASM_STAC
-	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
-	decl %ecx
-	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
-	leaq 8(%rdi),%rdi
-	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
-	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
-	ASM_CLAC
-	sfence
-	ret
-
-	.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
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 9734182966f3..7e48807b2fa1 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -6,7 +6,6 @@
  * for more details. No warranty for anything given at all.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 
@@ -47,23 +46,16 @@
 
 
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	cmpl	$3*64, %edx
 	jle	.Lignore
 
 .Lignore:
 	subq  $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 7*8
 	movq  %rbx, 2*8(%rsp)
-	CFI_REL_OFFSET rbx, 2*8
 	movq  %r12, 3*8(%rsp)
-	CFI_REL_OFFSET r12, 3*8
 	movq  %r14, 4*8(%rsp)
-	CFI_REL_OFFSET r14, 4*8
 	movq  %r13, 5*8(%rsp)
-	CFI_REL_OFFSET r13, 5*8
 	movq  %rbp, 6*8(%rsp)
-	CFI_REL_OFFSET rbp, 6*8
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -206,22 +198,14 @@ ENTRY(csum_partial_copy_generic)
 	addl %ebx, %eax
 	adcl %r9d, %eax		/* carry */
 
-	CFI_REMEMBER_STATE
 .Lende:
 	movq 2*8(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq 3*8(%rsp), %r12
-	CFI_RESTORE r12
 	movq 4*8(%rsp), %r14
-	CFI_RESTORE r14
 	movq 5*8(%rsp), %r13
-	CFI_RESTORE r13
 	movq 6*8(%rsp), %rbp
-	CFI_RESTORE rbp
 	addq $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -7*8
 	ret
-	CFI_RESTORE_STATE
 
 	/* Exception handlers. Very simple, zeroing is done in the wrappers */
 .Lbad_source:
@@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic)
 	jz   .Lende
 	movl $-EFAULT, (%rax)
 	jmp .Lende
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a4512359656a..46668cda4ffd 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
@@ -36,7 +35,6 @@
 
 	.text
 ENTRY(__get_user_1)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
@@ -45,11 +43,9 @@ ENTRY(__get_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-	CFI_STARTPROC
 	add $1,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -60,11 +56,9 @@ ENTRY(__get_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-	CFI_STARTPROC
 	add $3,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -75,11 +69,9 @@ ENTRY(__get_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	CFI_STARTPROC
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
@@ -104,28 +96,23 @@ ENTRY(__get_user_8)
 	ASM_CLAC
 	ret
 #endif
-	CFI_ENDPROC
 ENDPROC(__get_user_8)
 
 
 bad_get_user:
-	CFI_STARTPROC
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user)
 
 #ifdef CONFIG_X86_32
 bad_get_user_8:
-	CFI_STARTPROC
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user_8)
 #endif
 
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 05a95e713da8..33147fef3452 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -16,15 +16,12 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 /*
  * override generic version in lib/iomap_copy.c
  */
 ENTRY(__iowrite32_copy)
-	CFI_STARTPROC
 	movl %edx,%ecx
 	rep movsd
 	ret
-	CFI_ENDPROC
 ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index b046664f5a1c..16698bba87de 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,7 +2,6 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
 #include <asm/alternative-asm.h>
 
 /*
@@ -53,7 +52,6 @@ ENTRY(memcpy_erms)
 ENDPROC(memcpy_erms)
 
 ENTRY(memcpy_orig)
-	CFI_STARTPROC
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -178,5 +176,4 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-	CFI_ENDPROC
 ENDPROC(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0f8a0d0331b9..ca2afdd6d98e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,6 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -27,7 +26,6 @@
 
 ENTRY(memmove)
 ENTRY(__memmove)
-	CFI_STARTPROC
 
 	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
@@ -207,6 +205,5 @@ ENTRY(__memmove)
 	movb %r11b, (%rdi)
 13:
 	retq
-	CFI_ENDPROC
 ENDPROC(__memmove)
 ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb23976..2661fad05827 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,6 @@
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -66,7 +65,6 @@ ENTRY(memset_erms)
 ENDPROC(memset_erms)
 
 ENTRY(memset_orig)
-	CFI_STARTPROC
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -78,7 +76,6 @@ ENTRY(memset_orig)
 	movl  %edi,%r9d
 	andl  $7,%r9d
 	jnz  .Lbad_alignment
-	CFI_REMEMBER_STATE
 .Lafter_bad_alignment:
 
 	movq  %rdx,%rcx
@@ -128,7 +125,6 @@ ENTRY(memset_orig)
 	movq	%r10,%rax
 	ret
 
-	CFI_RESTORE_STATE
 .Lbad_alignment:
 	cmpq $7,%rdx
 	jbe	.Lhandle_7
@@ -139,5 +135,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-	CFI_ENDPROC
 ENDPROC(memset_orig)
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index c9f2d9ba8dd8..e5e3ed8dc079 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/asm.h>
 
 void *_mmx_memcpy(void *to, const void *from, size_t len)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 3ca5218fbece..c81556409bbb 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,5 @@
 #include <linux/linkage.h>
 #include <linux/errno.h>
-#include <asm/dwarf2.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -13,9 +12,8 @@
  */
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushq_cfi_reg rbx
-	pushq_cfi_reg rbp
+	pushq %rbx
+	pushq %rbp
 	movq	%rdi, %r10	/* Save pointer */
 	xorl	%r11d, %r11d	/* Return value */
 	movl    (%rdi), %eax
@@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs)
 	movl    20(%rdi), %ebp
 	movl    24(%rdi), %esi
 	movl    28(%rdi), %edi
-	CFI_REMEMBER_STATE
 1:	\op
 2:	movl    %eax, (%r10)
 	movl	%r11d, %eax	/* Return value */
@@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs)
 	movl    %ebp, 20(%r10)
 	movl    %esi, 24(%r10)
 	movl    %edi, 28(%r10)
-	popq_cfi_reg rbp
-	popq_cfi_reg rbx
+	popq %rbp
+	popq %rbx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, %r11d
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
@@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs)
 
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg ebp
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
-	pushl_cfi $0              /* Return value */
-	pushl_cfi %eax
+	pushl %ebx
+	pushl %ebp
+	pushl %esi
+	pushl %edi
+	pushl $0              /* Return value */
+	pushl %eax
 	movl    4(%eax), %ecx
 	movl    8(%eax), %edx
 	movl    12(%eax), %ebx
@@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs)
 	movl    24(%eax), %esi
 	movl    28(%eax), %edi
 	movl    (%eax), %eax
-	CFI_REMEMBER_STATE
 1:	\op
-2:	pushl_cfi %eax
+2:	pushl %eax
 	movl    4(%esp), %eax
-	popl_cfi (%eax)
+	popl (%eax)
 	addl    $4, %esp
-	CFI_ADJUST_CFA_OFFSET -4
 	movl    %ecx, 4(%eax)
 	movl    %edx, 8(%eax)
 	movl    %ebx, 12(%eax)
 	movl    %ebp, 20(%eax)
 	movl    %esi, 24(%eax)
 	movl    %edi, 28(%eax)
-	popl_cfi %eax
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebp
-	popl_cfi_reg ebx
+	popl %eax
+	popl %edi
+	popl %esi
+	popl %ebp
+	popl %ebx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, 4(%esp)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index fc6ba17a7eec..e0817a12d323 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,7 +11,6 @@
  * return value.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -30,11 +29,9 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	CFI_STARTPROC ; \
-		GET_THREAD_INFO(%_ASM_BX)
+#define ENTER	GET_THREAD_INFO(%_ASM_BX)
 #define EXIT	ASM_CLAC ;	\
-		ret ;		\
-		CFI_ENDPROC
+		ret
 
 .text
 ENTRY(__put_user_1)
@@ -87,7 +84,6 @@ ENTRY(__put_user_8)
 ENDPROC(__put_user_8)
 
 bad_put_user:
-	CFI_STARTPROC
 	movl $-EFAULT,%eax
 	EXIT
 END(bad_put_user)
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 2322abe4da3b..40027db99140 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,7 +15,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 #define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
 #define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
@@ -34,10 +33,10 @@
  */
 
 #define save_common_regs \
-	pushl_cfi_reg ecx
+	pushl %ecx
 
 #define restore_common_regs \
-	popl_cfi_reg ecx
+	popl %ecx
 
 	/* Avoid uglifying the argument copying x86-64 needs to do. */
 	.macro movq src, dst
@@ -64,50 +63,45 @@
  */
 
 #define save_common_regs \
-	pushq_cfi_reg rdi; \
-	pushq_cfi_reg rsi; \
-	pushq_cfi_reg rcx; \
-	pushq_cfi_reg r8;  \
-	pushq_cfi_reg r9;  \
-	pushq_cfi_reg r10; \
-	pushq_cfi_reg r11
+	pushq %rdi; \
+	pushq %rsi; \
+	pushq %rcx; \
+	pushq %r8;  \
+	pushq %r9;  \
+	pushq %r10; \
+	pushq %r11
 
 #define restore_common_regs \
-	popq_cfi_reg r11; \
-	popq_cfi_reg r10; \
-	popq_cfi_reg r9; \
-	popq_cfi_reg r8; \
-	popq_cfi_reg rcx; \
-	popq_cfi_reg rsi; \
-	popq_cfi_reg rdi
+	popq %r11; \
+	popq %r10; \
+	popq %r9; \
+	popq %r8; \
+	popq %rcx; \
+	popq %rsi; \
+	popq %rdi
 
 #endif
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_down_read_failed
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
-	CFI_STARTPROC
 	save_common_regs
 	movq %rax,%rdi
 	call rwsem_down_write_failed
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	CFI_STARTPROC
 	/* do nothing if still outstanding active readers */
 	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
 	jnz 1f
@@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake)
 	call rwsem_wake
 	restore_common_regs
 1:	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_wake)
 
 ENTRY(call_rwsem_downgrade_wake)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
deleted file mode 100644
index 5eb715087b80..000000000000
--- a/arch/x86/lib/thunk_32.S
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * 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>
-	#include <asm/asm.h>
-	#include <asm/dwarf2.h>
-
-	/* put return address in eax (arg1) */
-	.macro THUNK name, func, put_ret_addr_in_eax=0
-	.globl \name
-\name:
-	CFI_STARTPROC
-	pushl_cfi_reg eax
-	pushl_cfi_reg ecx
-	pushl_cfi_reg edx
-
-	.if \put_ret_addr_in_eax
-	/* Place EIP in the arg1 */
-	movl 3*4(%esp), %eax
-	.endif
-
-	call \func
-	popl_cfi_reg edx
-	popl_cfi_reg ecx
-	popl_cfi_reg eax
-	ret
-	CFI_ENDPROC
-	_ASM_NOKPROBE(\name)
-	.endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
-	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
-#ifdef CONFIG_PREEMPT
-	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
-#endif
-
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
deleted file mode 100644
index f89ba4e93025..000000000000
--- a/arch/x86/lib/thunk_64.S
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * 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.
- */
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm.h>
-
-	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
-	.macro THUNK name, func, put_ret_addr_in_rdi=0
-	.globl \name
-\name:
-	CFI_STARTPROC
-
-	/* this one pushes 9 elems, the next one would be %rIP */
-	pushq_cfi_reg rdi
-	pushq_cfi_reg rsi
-	pushq_cfi_reg rdx
-	pushq_cfi_reg rcx
-	pushq_cfi_reg rax
-	pushq_cfi_reg r8
-	pushq_cfi_reg r9
-	pushq_cfi_reg r10
-	pushq_cfi_reg r11
-
-	.if \put_ret_addr_in_rdi
-	/* 9*8(%rsp) is return addr on stack */
-	movq_cfi_restore 9*8, rdi
-	.endif
-
-	call \func
-	jmp  restore
-	CFI_ENDPROC
-	_ASM_NOKPROBE(\name)
-	.endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
-	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
-#endif
-
-#ifdef CONFIG_PREEMPT
-	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
-#endif
-
-#if defined(CONFIG_TRACE_IRQFLAGS) \
- || defined(CONFIG_DEBUG_LOCK_ALLOC) \
- || defined(CONFIG_PREEMPT)
-	CFI_STARTPROC
-	CFI_ADJUST_CFA_OFFSET 9*8
-restore:
-	popq_cfi_reg r11
-	popq_cfi_reg r10
-	popq_cfi_reg r9
-	popq_cfi_reg r8
-	popq_cfi_reg rax
-	popq_cfi_reg rcx
-	popq_cfi_reg rdx
-	popq_cfi_reg rsi
-	popq_cfi_reg rdi
-	ret
-	CFI_ENDPROC
-	_ASM_NOKPROBE(restore)
-#endif
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index e2f5e21c03b3..91d93b95bd86 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user);
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *