Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/kernel/Makefile
	include/asm-x86/pda.h

48 files changed, 206 insertions, 50 deletions

diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index 55e57a1c2e6d..1154d924080b 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -47,3 +47,5 @@ ENTRY(__aeabi_llsl)
 	mov	al, al, lsl r2
 	mov	pc, lr
 
+ENDPROC(__ashldi3)
+ENDPROC(__aeabi_llsl)
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index 0b31398f89b2..9f8b35572f8c 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -47,3 +47,5 @@ ENTRY(__aeabi_lasr)
 	mov	ah, ah, asr r2
 	mov	pc, lr
 
+ENDPROC(__ashrdi3)
+ENDPROC(__aeabi_lasr)
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index 84dc890d2bf3..b0951d0e8b2c 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -30,6 +30,8 @@ ENTRY(c_backtrace)
 
 #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
 		mov	pc, lr
+ENDPROC(__backtrace)
+ENDPROC(c_backtrace)
 #else
 		stmfd	sp!, {r4 - r8, lr}	@ Save an extra register so we have a location...
 		movs	frame, r0		@ if frame pointer is zero
@@ -103,6 +105,8 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		mov	r1, frame
 		bl	printk
 no_frame:	ldmfd	sp!, {r4 - r8, pc}
+ENDPROC(__backtrace)
+ENDPROC(c_backtrace)
 		
 		.section __ex_table,"a"
 		.align	3
diff --git a/arch/arm/lib/changebit.S b/arch/arm/lib/changebit.S
index 389567c24090..80f3115cbee2 100644
--- a/arch/arm/lib/changebit.S
+++ b/arch/arm/lib/changebit.S
@@ -19,3 +19,5 @@ ENTRY(_change_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_change_bit_le)
 	bitop	eor
+ENDPROC(_change_bit_be)
+ENDPROC(_change_bit_le)
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index ecb28dcdaf7b..4d6bc71231f3 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -41,9 +41,10 @@ USER(		strplt	r2, [r0], #4)
 USER(		strnebt	r2, [r0], #1)
 USER(		strnebt	r2, [r0], #1)
 		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
-USER(		strnebt	r2, [r0], #1)
+USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
+ENDPROC(__clear_user)
 
 		.section .fixup,"ax"
 		.align	0
diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S
index 347516533025..1a63e43a1df0 100644
--- a/arch/arm/lib/clearbit.S
+++ b/arch/arm/lib/clearbit.S
@@ -20,3 +20,5 @@ ENTRY(_clear_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_clear_bit_le)
 	bitop	bic
+ENDPROC(_clear_bit_be)
+ENDPROC(_clear_bit_le)
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 6b7363ce749c..56799a165cc4 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -87,6 +87,8 @@ ENTRY(__copy_from_user)
 
 #include "copy_template.S"
 
+ENDPROC(__copy_from_user)
+
 	.section .fixup,"ax"
 	.align 0
 	copy_abort_preamble
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 666c99cc0744..6ae04db1ca4f 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -44,3 +44,4 @@ ENTRY(copy_page)
 	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
 	PLD(	beq	2b			)
 		ldmfd	sp!, {r4, pc}			@	3
+ENDPROC(copy_page)
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index cab355c0c1f7..139cce646055 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -13,14 +13,6 @@
  */
 
 /*
- * This can be used to enable code to cacheline align the source pointer.
- * Experiments on tested architectures (StrongARM and XScale) didn't show
- * this a worthwhile thing to do.  That might be different in the future.
- */
-//#define CALGN(code...)	code
-#define CALGN(code...)
-
-/*
  * Theory of operation
  * -------------------
  *
@@ -82,7 +74,7 @@
 		stmfd	sp!, {r5 - r8}
 		blt	5f
 
-	CALGN(	ands	ip, r1, #31		)
+	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	r3, ip, #32		)
 	CALGN(	sbcnes	r4, r3, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
@@ -168,7 +160,7 @@
 		subs	r2, r2, #28
 		blt	14f
 
-	CALGN(	ands	ip, r1, #31		)
+	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	ip, ip, #32		)
 	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 5224d94688d9..22f968bbdffd 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -90,6 +90,8 @@ ENTRY(__copy_to_user)
 
 #include "copy_template.S"
 
+ENDPROC(__copy_to_user)
+
 	.section .fixup,"ax"
 	.align 0
 	copy_abort_preamble
diff --git a/arch/arm/lib/csumipv6.S b/arch/arm/lib/csumipv6.S
index 9621469beec1..3ac6ef01bc43 100644
--- a/arch/arm/lib/csumipv6.S
+++ b/arch/arm/lib/csumipv6.S
@@ -29,4 +29,5 @@ ENTRY(__csum_ipv6_magic)
 		adcs	r0, r0, r2
 		adcs	r0, r0, #0
 		ldmfd	sp!, {pc}
+ENDPROC(__csum_ipv6_magic)
 
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index a78dae5a7b28..31d3cb34740d 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -139,3 +139,4 @@ ENTRY(csum_partial)
 		tst	len, #0x1c
 		bne	4b
 		b	.Lless4
+ENDPROC(csum_partial)
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
index 21effe0dbf97..d03fc71fc88c 100644
--- a/arch/arm/lib/csumpartialcopy.S
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -18,13 +18,11 @@
  */
 
 		.macro	save_regs
-		mov	ip, sp
-		stmfd	sp!, {r1, r4 - r8, fp, ip, lr, pc}
-		sub	fp, ip, #4
+		stmfd	sp!, {r1, r4 - r8, lr}
 		.endm
 
 		.macro	load_regs
-		ldmfd	sp, {r1, r4 - r8, fp, sp, pc}
+		ldmfd	sp!, {r1, r4 - r8, pc}
 		.endm
 
 		.macro	load1b, reg1
@@ -50,5 +48,6 @@
 		.endm
 
 #define FN_ENTRY	ENTRY(csum_partial_copy_nocheck)
+#define FN_EXIT		ENDPROC(csum_partial_copy_nocheck)
 
 #include "csumpartialcopygeneric.S"
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index c50e8f5285d1..d620a5f22a09 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -329,3 +329,4 @@ FN_ENTRY
 		adcs	sum, sum, r4, push #24
 		mov	r5, r4, get_byte_1
 		b	.Lexit
+FN_EXIT
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index c3b93e22ea25..14677fb4b0c4 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -18,13 +18,11 @@
 		.text
 
 		.macro	save_regs
-		mov	ip, sp
-		stmfd	sp!, {r1 - r2, r4 - r8, fp, ip, lr, pc}
-		sub	fp, ip, #4
+		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
 
 		.macro	load_regs
-		ldmfd	sp, {r1, r2, r4-r8, fp, sp, pc}
+		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
 
 		.macro	load1b,	reg1
@@ -82,6 +80,7 @@
  */
 
 #define FN_ENTRY	ENTRY(csum_partial_copy_from_user)
+#define FN_EXIT		ENDPROC(csum_partial_copy_from_user)
 
 #include "csumpartialcopygeneric.S"
 
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay.S
index 930a70259220..8d6a8762ab88 100644
--- a/arch/arm/lib/delay.S
+++ b/arch/arm/lib/delay.S
@@ -60,3 +60,6 @@ ENTRY(__delay)
 #endif
 		bhi	__delay
 		mov	pc, lr
+ENDPROC(__udelay)
+ENDPROC(__const_udelay)
+ENDPROC(__delay)
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index 58eef6607629..1425e789ba86 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -198,3 +198,4 @@ ENTRY(__do_div64)
 	mov	xh, #0
 	ldr	pc, [sp], #8
 
+ENDPROC(__do_div64)
diff --git a/arch/arm/lib/ecard.S b/arch/arm/lib/ecard.S
index c55aaa2a2088..8678eb2b7a60 100644
--- a/arch/arm/lib/ecard.S
+++ b/arch/arm/lib/ecard.S
@@ -12,7 +12,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/hardware.h>
+#include <mach/hardware.h>
 
 #define CPSR2SPSR(rt) \
 		mrs	rt, cpsr; \
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index a5ca0248aa4e..8c4defc4f3c4 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -33,6 +33,7 @@ ENTRY(_find_first_zero_bit_le)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_zero_bit_le)
 
 /*
  * Purpose  : Find next 'zero' bit
@@ -50,6 +51,7 @@ ENTRY(_find_next_zero_bit_le)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_le)
 
 /*
  * Purpose  : Find a 'one' bit
@@ -67,6 +69,7 @@ ENTRY(_find_first_bit_le)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_bit_le)
 
 /*
  * Purpose  : Find next 'one' bit
@@ -83,6 +86,7 @@ ENTRY(_find_next_bit_le)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_le)
 
 #ifdef __ARMEB__
 
@@ -99,6 +103,7 @@ ENTRY(_find_first_zero_bit_be)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_zero_bit_be)
 
 ENTRY(_find_next_zero_bit_be)
 		teq	r1, #0
@@ -113,6 +118,7 @@ ENTRY(_find_next_zero_bit_be)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_be)
 
 ENTRY(_find_first_bit_be)
 		teq	r1, #0
@@ -127,6 +133,7 @@ ENTRY(_find_first_bit_be)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_bit_be)
 
 ENTRY(_find_next_bit_be)
 		teq	r1, #0
@@ -140,6 +147,7 @@ ENTRY(_find_next_bit_be)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_be)
 
 #endif
 
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 1dd8ea4f9a9c..6763088b7607 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -20,22 +20,22 @@
  *		r2, r3 contains the zero-extended value
  *		lr corrupted
  *
- * No other registers must be altered.  (see include/asm-arm/uaccess.h
+ * No other registers must be altered.  (see <asm/uaccess.h>
  * for specific ASM register usage).
  *
  * Note that ADDR_LIMIT is either 0 or 0xc0000000.
  * Note also that it is intended that __get_user_bad is not global.
  */
+#include <linux/linkage.h>
 #include <asm/errno.h>
 
-	.global	__get_user_1
-__get_user_1:
+ENTRY(__get_user_1)
 1:	ldrbt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_1)
 
-	.global	__get_user_2
-__get_user_2:
+ENTRY(__get_user_2)
 2:	ldrbt	r2, [r0], #1
 3:	ldrbt	r3, [r0]
 #ifndef __ARMEB__
@@ -45,17 +45,19 @@ __get_user_2:
 #endif
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_2)
 
-	.global	__get_user_4
-__get_user_4:
+ENTRY(__get_user_4)
 4:	ldrt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_4)
 
 __get_user_bad:
 	mov	r2, #0
 	mov	r0, #-EFAULT
 	mov	pc, lr
+ENDPROC(__get_user_bad)
 
 .section __ex_table, "a"
 	.long	1b, __get_user_bad
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index fb966ad0276f..9f4238987fe9 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -120,3 +120,4 @@ ENTRY(__raw_readsb)
 		strgtb	r3, [r1]
 
 		ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(__raw_readsb)
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 75a9121cb23f..5fb97e7f9f4b 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -76,3 +76,4 @@ ENTRY(__raw_readsl)
 8:		mov	r3, ip, get_byte_0
 		strb	r3, [r1, #0]
 		mov	pc, lr
+ENDPROC(__raw_readsl)
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
index 4ef904185142..9aaf7c72065d 100644
--- a/arch/arm/lib/io-readsw-armv3.S
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -9,7 +9,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/hardware.h>
+#include <mach/hardware.h>
 
 .Linsw_bad_alignment:
 		adr	r0, .Linsw_bad_align_msg
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index 4db1c5f0b219..1f393d42593d 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -128,3 +128,4 @@ ENTRY(__raw_readsw)
    _BE_ONLY_(	movne	ip, ip, lsr #24		)
 		strneb	ip, [r1]
 		ldmfd	sp!, {r4, pc}
+ENDPROC(__raw_readsw)
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
index 7eba2b6cc69f..68b92f4acaeb 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -91,3 +91,4 @@ ENTRY(__raw_writesb)
 		strgtb	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
+ENDPROC(__raw_writesb)
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index f8f14dd227ca..8d3b7813725c 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -64,3 +64,4 @@ ENTRY(__raw_writesl)
 		str	ip, [r0]
 		bne	6b
 		mov	pc, lr
+ENDPROC(__raw_writesl)
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
index 1607a29f49b7..cd34503e424d 100644
--- a/arch/arm/lib/io-writesw-armv3.S
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -9,7 +9,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/hardware.h>
+#include <mach/hardware.h>
 
 .Loutsw_bad_alignment:
 		adr	r0, .Loutsw_bad_align_msg
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index c8e85bd653b7..d6585612c86b 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -94,3 +94,4 @@ ENTRY(__raw_writesw)
 3:		movne	ip, r3, lsr #8
 		strneh	ip, [r0]
 		mov	pc, lr
+ENDPROC(__raw_writesw)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 4e492f4b3f0e..67964bcfc854 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -230,6 +230,8 @@ ENTRY(__aeabi_uidiv)
 	mov	r0, r0, lsr r2
 	mov	pc, lr
 
+ENDPROC(__udivsi3)
+ENDPROC(__aeabi_uidiv)
 
 ENTRY(__umodsi3)
 
@@ -245,6 +247,7 @@ ENTRY(__umodsi3)
 
 	mov	pc, lr
 
+ENDPROC(__umodsi3)
 
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
@@ -284,6 +287,8 @@ ENTRY(__aeabi_idiv)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+ENDPROC(__divsi3)
+ENDPROC(__aeabi_idiv)
 
 ENTRY(__modsi3)
 
@@ -305,6 +310,8 @@ ENTRY(__modsi3)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+ENDPROC(__modsi3)
+
 #ifdef CONFIG_AEABI
 
 ENTRY(__aeabi_uidivmod)
@@ -316,6 +323,8 @@ ENTRY(__aeabi_uidivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+ENDPROC(__aeabi_uidivmod)
+
 ENTRY(__aeabi_idivmod)
 
 	stmfd	sp!, {r0, r1, ip, lr}
@@ -325,6 +334,8 @@ ENTRY(__aeabi_idivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+ENDPROC(__aeabi_idivmod)
+
 #endif
 
 Ldiv0:
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index a86dbdd59cc4..99ea338bf87c 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -47,3 +47,5 @@ ENTRY(__aeabi_llsr)
 	mov	ah, ah, lsr r2
 	mov	pc, lr
 
+ENDPROC(__lshrdi3)
+ENDPROC(__aeabi_llsr)
diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S
index e7ab1ea8ebaa..1da86991d700 100644
--- a/arch/arm/lib/memchr.S
+++ b/arch/arm/lib/memchr.S
@@ -23,3 +23,4 @@ ENTRY(memchr)
 	sub	r0, r0, #1
 2:	movne	r0, #0
 	mov	pc, lr
+ENDPROC(memchr)
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 7e71d6708a8d..e0d002641d3f 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -57,3 +57,4 @@ ENTRY(memcpy)
 
 #include "copy_template.S"
 
+ENDPROC(memcpy)
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index ef7fddc14ac9..12549187088c 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -13,14 +13,6 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-/*
- * This can be used to enable code to cacheline align the source pointer.
- * Experiments on tested architectures (StrongARM and XScale) didn't show
- * this a worthwhile thing to do.  That might be different in the future.
- */
-//#define CALGN(code...)        code
-#define CALGN(code...)
-
 		.text
 
 /*
@@ -55,11 +47,12 @@ ENTRY(memmove)
 		stmfd	sp!, {r5 - r8}
 		blt	5f
 
-	CALGN(	ands	ip, r1, #31		)
+	CALGN(	ands	ip, r0, #31		)
 	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
 	CALGN(	adr	r4, 6f			)
 	CALGN(	subs	r2, r2, ip		)  @ C is set here
+	CALGN(	rsb	ip, ip, #32		)
 	CALGN(	add	pc, r4, ip		)
 
 	PLD(	pld	[r1, #-4]		)
@@ -138,8 +131,7 @@ ENTRY(memmove)
 		subs	r2, r2, #28
 		blt	14f
 
-	CALGN(	ands	ip, r1, #31		)
-	CALGN(	rsb	ip, ip, #32		)
+	CALGN(	ands	ip, r0, #31		)
 	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
@@ -204,3 +196,4 @@ ENTRY(memmove)
 
 18:		backward_copy_shift	push=24	pull=8
 
+ENDPROC(memmove)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 95b110b07a89..761eefa76243 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -39,6 +39,9 @@ ENTRY(memset)
 	mov	r3, r1
 	cmp	r2, #16
 	blt	4f
+
+#if ! CALGN(1)+0
+
 /*
  * We need an extra register for this loop - save the return address and
  * use the LR
@@ -64,6 +67,49 @@ ENTRY(memset)
 	stmneia	r0!, {r1, r3, ip, lr}
 	ldr	lr, [sp], #4
 
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+	stmfd	sp!, {r4-r7, lr}
+	mov	r4, r1
+	mov	r5, r1
+	mov	r6, r1
+	mov	r7, r1
+	mov	ip, r1
+	mov	lr, r1
+
+	cmp	r2, #96
+	tstgt	r0, #31
+	ble	3f
+
+	and	ip, r0, #31
+	rsb	ip, ip, #32
+	sub	r2, r2, ip
+	movs	ip, ip, lsl #(32 - 4)
+	stmcsia	r0!, {r4, r5, r6, r7}
+	stmmiia	r0!, {r4, r5}
+	tst	ip, #(1 << 30)
+	mov	ip, r1
+	strne	r1, [r0], #4
+
+3:	subs	r2, r2, #64
+	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	bgt	3b
+	ldmeqfd	sp!, {r4-r7, pc}
+
+	tst	r2, #32
+	stmneia	r0!, {r1, r3-r7, ip, lr}
+	tst	r2, #16
+	stmneia	r0!, {r4-r7}
+	ldmfd	sp!, {r4-r7, lr}
+
+#endif
+
 4:	tst	r2, #8
 	stmneia	r0!, {r1, r3}
 	tst	r2, #4
@@ -78,3 +124,4 @@ ENTRY(memset)
 	tst	r2, #1
 	strneb	r1, [r0], #1
 	mov	pc, lr
+ENDPROC(memset)
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
index abf2508e8221..3fbdef5f802a 100644
--- a/arch/arm/lib/memzero.S
+++ b/arch/arm/lib/memzero.S
@@ -39,6 +39,9 @@ ENTRY(__memzero)
  */
 	cmp	r1, #16			@ 1 we can skip this chunk if we
 	blt	4f			@ 1 have < 16 bytes
+
+#if ! CALGN(1)+0
+
 /*
  * We need an extra register for this loop - save the return address and
  * use the LR
@@ -64,6 +67,47 @@ ENTRY(__memzero)
 	stmneia	r0!, {r2, r3, ip, lr}	@ 4
 	ldr	lr, [sp], #4		@ 1
 
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+	stmfd	sp!, {r4-r7, lr}
+	mov	r4, r2
+	mov	r5, r2
+	mov	r6, r2
+	mov	r7, r2
+	mov	ip, r2
+	mov	lr, r2
+
+	cmp	r1, #96
+	andgts	ip, r0, #31
+	ble	3f
+
+	rsb	ip, ip, #32
+	sub	r1, r1, ip
+	movs	ip, ip, lsl #(32 - 4)
+	stmcsia	r0!, {r4, r5, r6, r7}
+	stmmiia	r0!, {r4, r5}
+	movs	ip, ip, lsl #2
+	strcs	r2, [r0], #4
+
+3:	subs	r1, r1, #64
+	stmgeia	r0!, {r2-r7, ip, lr}
+	stmgeia	r0!, {r2-r7, ip, lr}
+	bgt	3b
+	ldmeqfd	sp!, {r4-r7, pc}
+
+	tst	r1, #32
+	stmneia	r0!, {r2-r7, ip, lr}
+	tst	r1, #16
+	stmneia	r0!, {r4-r7}
+	ldmfd	sp!, {r4-r7, lr}
+
+#endif
+
 4:	tst	r1, #8			@ 1 8 bytes or more?
 	stmneia	r0!, {r2, r3}		@ 2
 	tst	r1, #4			@ 1 4 bytes or more?
@@ -78,3 +122,4 @@ ENTRY(__memzero)
 	tst	r1, #1			@ 1 a byte left over
 	strneb	r2, [r0], #1		@ 1
 	mov	pc, lr			@ 1
+ENDPROC(__memzero)
diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S
index d89c60615794..36c91b4957e2 100644
--- a/arch/arm/lib/muldi3.S
+++ b/arch/arm/lib/muldi3.S
@@ -43,3 +43,5 @@ ENTRY(__aeabi_lmul)
 	adc	xh, xh, ip, lsr #16
 	mov	pc, lr
 
+ENDPROC(__muldi3)
+ENDPROC(__aeabi_lmul)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 8620afe54f72..864f3c1c4f18 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -20,22 +20,22 @@
  * Outputs:	r0 is the error code
  *		lr corrupted
  *
- * No other registers must be altered.  (see include/asm-arm/uaccess.h
+ * No other registers must be altered.  (see <asm/uaccess.h>
  * for specific ASM register usage).
  *
  * Note that ADDR_LIMIT is either 0 or 0xc0000000
  * Note also that it is intended that __put_user_bad is not global.
  */
+#include <linux/linkage.h>
 #include <asm/errno.h>
 
-	.global	__put_user_1
-__put_user_1:
+ENTRY(__put_user_1)
 1:	strbt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_1)
 
-	.global	__put_user_2
-__put_user_2:
+ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
 #ifndef __ARMEB__
 2:	strbt	r2, [r0], #1
@@ -46,23 +46,25 @@ __put_user_2:
 #endif
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_2)
 
-	.global	__put_user_4
-__put_user_4:
+ENTRY(__put_user_4)
 4:	strt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_4)
 
-	.global	__put_user_8
-__put_user_8:
+ENTRY(__put_user_8)
 5:	strt	r2, [r0], #4
 6:	strt	r3, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_8)
 
 __put_user_bad:
 	mov	r0, #-EFAULT
 	mov	pc, lr
+ENDPROC(__put_user_bad)
 
 .section __ex_table, "a"
 	.long	1b, __put_user_bad
diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S
index 83bc23d5b037..1dd7176c4b2b 100644
--- a/arch/arm/lib/setbit.S
+++ b/arch/arm/lib/setbit.S
@@ -20,3 +20,5 @@ ENTRY(_set_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_set_bit_le)
 	bitop	orr
+ENDPROC(_set_bit_be)
+ENDPROC(_set_bit_le)
diff --git a/arch/arm/lib/sha1.S b/arch/arm/lib/sha1.S
index ff6ece487ffc..a16fb208c841 100644
--- a/arch/arm/lib/sha1.S
+++ b/arch/arm/lib/sha1.S
@@ -29,7 +29,7 @@ ENTRY(sha_transform)
 	stmfd	sp!, {r4 - r8, lr}
 
 	@ for (i = 0; i < 16; i++)
-	@         W[i] = be32_to_cpu(in[i]); */
+	@         W[i] = be32_to_cpu(in[i]);
 
 #ifdef __ARMEB__
 	mov	r4, r0
@@ -185,6 +185,8 @@ ENTRY(sha_transform)
 
 	ldmfd	sp!, {r4 - r8, pc}
 
+ENDPROC(sha_transform)
+
 .L_sha_K:
 	.word	0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
 
@@ -204,3 +206,4 @@ ENTRY(sha_init)
 	stmia	r0, {r1, r2, r3, ip, lr}
 	ldr	pc, [sp], #4
 
+ENDPROC(sha_init)
diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S
index 9f18d6fdee6a..d8f2a1c1aea4 100644
--- a/arch/arm/lib/strchr.S
+++ b/arch/arm/lib/strchr.S
@@ -24,3 +24,4 @@ ENTRY(strchr)
 		movne	r0, #0
 		subeq	r0, r0, #1
 		mov	pc, lr
+ENDPROC(strchr)
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
index 36e3741a3772..330373c26dd9 100644
--- a/arch/arm/lib/strncpy_from_user.S
+++ b/arch/arm/lib/strncpy_from_user.S
@@ -31,6 +31,7 @@ USER(	ldrplbt	r3, [r1], #1)
 	sub	r1, r1, #1	@ take NUL character out of count
 2:	sub	r0, r1, ip
 	mov	pc, lr
+ENDPROC(__strncpy_from_user)
 
 	.section .fixup,"ax"
 	.align	0
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
index 18d8fa4f925a..90bb9d020836 100644
--- a/arch/arm/lib/strnlen_user.S
+++ b/arch/arm/lib/strnlen_user.S
@@ -31,6 +31,7 @@ USER(	ldrbt	r3, [r0], #1)
 	add	r0, r0, #1
 2:	sub	r0, r0, r2
 	mov	pc, lr
+ENDPROC(__strnlen_user)
 
 	.section .fixup,"ax"
 	.align	0
diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S
index 538df220aa48..302f20cd2423 100644
--- a/arch/arm/lib/strrchr.S
+++ b/arch/arm/lib/strrchr.S
@@ -23,3 +23,4 @@ ENTRY(strrchr)
 		bne	1b
 		mov	r0, r3
 		mov	pc, lr
+ENDPROC(strrchr)
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
index b25dcd2be53e..5c98dc567f0f 100644
--- a/arch/arm/lib/testchangebit.S
+++ b/arch/arm/lib/testchangebit.S
@@ -16,3 +16,5 @@ ENTRY(_test_and_change_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_change_bit_le)
 	testop	eor, strb
+ENDPROC(_test_and_change_bit_be)
+ENDPROC(_test_and_change_bit_le)
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 2dcc4b16b68e..543d7094d18e 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -16,3 +16,5 @@ ENTRY(_test_and_clear_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_clear_bit_le)
 	testop	bicne, strneb
+ENDPROC(_test_and_clear_bit_be)
+ENDPROC(_test_and_clear_bit_le)
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
index 9011c969761a..0b3f390401ce 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -16,3 +16,5 @@ ENTRY(_test_and_set_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_set_bit_le)
 	testop	orreq, streqb
+ENDPROC(_test_and_set_bit_be)
+ENDPROC(_test_and_set_bit_le)
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index b48bd6d5fd83..ffdd27498cee 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -277,6 +277,7 @@ USER(		strgebt	r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
 USER(		strgtbt	r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
+ENDPROC(__copy_to_user)
 
 		.section .fixup,"ax"
 		.align	0
@@ -542,6 +543,7 @@ USER(		ldrgebt	r3, [r1], #1)			@ May fault
 USER(		ldrgtbt	r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
+ENDPROC(__copy_from_user)
 
 		.section .fixup,"ax"
 		.align	0
diff --git a/arch/arm/lib/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S
index f76de07ac182..f0df6a91db04 100644
--- a/arch/arm/lib/ucmpdi2.S
+++ b/arch/arm/lib/ucmpdi2.S
@@ -33,6 +33,8 @@ ENTRY(__ucmpdi2)
 	movhi	r0, #2
 	mov	pc, lr
 
+ENDPROC(__ucmpdi2)
+
 #ifdef CONFIG_AEABI
 
 ENTRY(__aeabi_ulcmp)
@@ -44,5 +46,7 @@ ENTRY(__aeabi_ulcmp)
 	movhi	r0, #1
 	mov	pc, lr
 
+ENDPROC(__aeabi_ulcmp)
+
 #endif