25 files changed, 106 insertions, 106 deletions

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index ad25fd1872c7..0bff0176db2c 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -39,7 +39,7 @@ $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  NEON_FLAGS			:= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
   CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 93cddab73072..95bd35991288 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -7,7 +7,7 @@
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -32,7 +32,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -62,7 +62,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r2, r0, #31
 	mov	r0, r0, lsr #5
 	mov	r3, #1
@@ -89,7 +89,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r3, r0, #31
 	mov	r0, r0, lsr #5
 	save_and_disable_irqs ip
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index e936352ccb00..55946e3fa2ba 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -44,7 +44,7 @@ UNWIND(.save {r1, lr})
 		strusr	r2, r0, 1, ne, rept=2
 		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
 		it	ne			@ explicit IT needed for the label
-USER(		strnebt	r2, [r0])
+USER(		strbtne	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
 UNWIND(.fnend)
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 0d4c189c7f4f..6a3419e2c6d8 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -91,7 +91,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-	str\cond\()b \reg, [\ptr], #1
+	strb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 6ee2f6706f86..b84ce1792043 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -39,9 +39,9 @@ ENTRY(copy_page)
 	.endr
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
+		ldmiagt	r1!, {r3, r4, ip, lr}		@	4
 		bgt	1b				@	1
-	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
+	PLD(	ldmiaeq 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 652e4d98cd47..a11f2c25e03a 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -99,7 +99,7 @@
 
 	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	r3, ip, #32		)
-	CALGN(	sbcnes	r4, r3, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, r3, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
 	CALGN(	adr	r4, 6f			)
 	CALGN(	subs	r2, r2, r3		)  @ C gets set
@@ -204,7 +204,7 @@
 
 	CALGN(	ands	ip, r0, #31		)
 	CALGN(	rsb	ip, ip, #32		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
@@ -241,7 +241,7 @@
 		orr	r9, r9, ip, lspush #\push
 		mov	ip, ip, lspull #\pull
 		orr	ip, ip, lr, lspush #\push
-		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
+		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	13b			)
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 97a6ff4b7e3c..c7d08096e354 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -49,7 +49,7 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
-	ldr\cond\()b \reg, [\ptr], #1
+	ldrb\cond \reg, [\ptr], #1
 	.endm
 
 #ifdef CONFIG_CPU_USE_DOMAINS
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index 984e0f29d548..bd84e2db353b 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -40,9 +40,9 @@ td3	.req	lr
 		/* we must have at least one byte. */
 		tst	buf, #1			@ odd address?
 		movne	sum, sum, ror #8
-		ldrneb	td0, [buf], #1
+		ldrbne	td0, [buf], #1
 		subne	len, len, #1
-		adcnes	sum, sum, td0, put_byte_1
+		adcsne	sum, sum, td0, put_byte_1
 
 .Lless4:		tst	len, #6
 		beq	.Lless8_byte
@@ -68,8 +68,8 @@ td3	.req	lr
 		bne	.Lless8_wordlp
 
 .Lless8_byte:	tst	len, #1			@ odd number of bytes
-		ldrneb	td0, [buf], #1		@ include last byte
-		adcnes	sum, sum, td0, put_byte_0	@ update checksum
+		ldrbne	td0, [buf], #1		@ include last byte
+		adcsne	sum, sum, td0, put_byte_0	@ update checksum
 
 .Ldone:		adc	r0, sum, #0		@ collect up the last carry
 		ldr	td0, [sp], #4
@@ -78,17 +78,17 @@ td3	.req	lr
 		ldr	pc, [sp], #4		@ return
 
 .Lnot_aligned:	tst	buf, #1			@ odd address
-		ldrneb	td0, [buf], #1		@ make even
+		ldrbne	td0, [buf], #1		@ make even
 		subne	len, len, #1
-		adcnes	sum, sum, td0, put_byte_1	@ update checksum
+		adcsne	sum, sum, td0, put_byte_1	@ update checksum
 
 		tst	buf, #2			@ 32-bit aligned?
 #if __LINUX_ARM_ARCH__ >= 4
-		ldrneh	td0, [buf], #2		@ make 32-bit aligned
+		ldrhne	td0, [buf], #2		@ make 32-bit aligned
 		subne	len, len, #2
 #else
-		ldrneb	td0, [buf], #1
-		ldrneb	ip, [buf], #1
+		ldrbne	td0, [buf], #1
+		ldrbne	ip, [buf], #1
 		subne	len, len, #2
 #ifndef __ARMEB__
 		orrne	td0, td0, ip, lsl #8
@@ -96,7 +96,7 @@ td3	.req	lr
 		orrne	td0, ip, td0, lsl #8
 #endif
 #endif
-		adcnes	sum, sum, td0		@ update checksum
+		adcsne	sum, sum, td0		@ update checksum
 		ret	lr
 
 ENTRY(csum_partial)
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index 10b45909610c..08e17758cbea 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -148,9 +148,9 @@ FN_ENTRY
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 .Lexit:		tst	len, #1
-		strneb	r5, [dst], #1
+		strbne	r5, [dst], #1
 		andne	r5, r5, #255
-		adcnes	sum, sum, r5, put_byte_0
+		adcsne	sum, sum, r5, put_byte_0
 
 		/*
 		 * If the dst pointer was not 16-bit aligned, we
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index b83fdc06286a..f4716d98e0b4 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -95,7 +95,7 @@
 		add	r2, r2, r1
 		mov	r0, #0			@ zero the buffer
 9002:		teq	r2, r1
-		strneb	r0, [r1], #1
+		strbne	r0, [r1], #1
 		bne	9002b
 		load_regs
 		.popsection
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index a9eafe4981eb..4d80f690c48b 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -88,8 +88,8 @@ UNWIND(.fnstart)
  	@ Break out early if dividend reaches 0.
 2:	cmp	xh, yl
 	orrcs	yh, yh, ip
-	subcss	xh, xh, yl
-	movnes	ip, ip, lsr #1
+	subscs	xh, xh, yl
+	movsne	ip, ip, lsr #1
 	mov	yl, yl, lsr #1
 	bne	2b
 
diff --git a/arch/arm/lib/floppydma.S b/arch/arm/lib/floppydma.S
index 617150b1baef..de68d3b343e3 100644
--- a/arch/arm/lib/floppydma.S
+++ b/arch/arm/lib/floppydma.S
@@ -14,8 +14,8 @@
 		.global	floppy_fiqin_end
 ENTRY(floppy_fiqin_start)
 		subs	r9, r9, #1
-		ldrgtb	r12, [r11, #-4]
-		ldrleb	r12, [r11], #0
+		ldrbgt	r12, [r11, #-4]
+		ldrble	r12, [r11], #0
 		strb	r12, [r10], #1
 		subs	pc, lr, #4
 floppy_fiqin_end:
@@ -23,10 +23,10 @@ floppy_fiqin_end:
 		.global	floppy_fiqout_end
 ENTRY(floppy_fiqout_start)
 		subs	r9, r9, #1
-		ldrgeb	r12, [r10], #1
+		ldrbge	r12, [r10], #1
 		movlt	r12, #0
-		strleb	r12, [r11], #0
-		subles	pc, lr, #4
+		strble	r12, [r11], #0
+		subsle	pc, lr, #4
 		strb	r12, [r11, #-4]
 		subs	pc, lr, #4
 floppy_fiqout_end:
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index c31b2f3153f1..91038a0a77b5 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -16,10 +16,10 @@
 		cmp	ip, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
-		ldrgeb	r3, [r0]
-		strgeb	r3, [r1], #1
-		ldrgtb	r3, [r0]
-		strgtb	r3, [r1], #1
+		ldrbge	r3, [r0]
+		strbge	r3, [r1], #1
+		ldrbgt	r3, [r0]
+		strbgt	r3, [r1], #1
 		subs	r2, r2, ip
 		bne	.Linsb_aligned
 
@@ -72,7 +72,7 @@ ENTRY(__raw_readsb)
 		bpl	.Linsb_16_lp
 
 		tst	r2, #15
-		ldmeqfd	sp!, {r4 - r6, pc}
+		ldmfdeq	sp!, {r4 - r6, pc}
 
 .Linsb_no_16:	tst	r2, #8
 		beq	.Linsb_no_8
@@ -109,15 +109,15 @@ ENTRY(__raw_readsb)
 		str	r3, [r1], #4
 
 .Linsb_no_4:	ands	r2, r2, #3
-		ldmeqfd	sp!, {r4 - r6, pc}
+		ldmfdeq	sp!, {r4 - r6, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
-		ldrgeb	r3, [r0]
-		strgeb	r3, [r1], #1
-		ldrgtb	r3, [r0]
-		strgtb	r3, [r1]
+		ldrbge	r3, [r0]
+		strbge	r3, [r1], #1
+		ldrbgt	r3, [r0]
+		strbgt	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 2ed86fa5465f..f2e2064318d2 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -30,7 +30,7 @@ ENTRY(__raw_readsl)
 2:		movs	r2, r2, lsl #31
 		ldrcs	r3, [r0, #0]
 		ldrcs	ip, [r0, #0]
-		stmcsia	r1!, {r3, ip}
+		stmiacs	r1!, {r3, ip}
 		ldrne	r3, [r0, #0]
 		strne	r3, [r1, #0]
 		ret	lr
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
index 413da9914529..8b25b69c516e 100644
--- a/arch/arm/lib/io-readsw-armv3.S
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -68,7 +68,7 @@ ENTRY(__raw_readsw)
 		bpl	.Linsw_8_lp
 
 		tst	r2, #7
-		ldmeqfd	sp!, {r4, r5, r6, pc}
+		ldmfdeq	sp!, {r4, r5, r6, pc}
 
 .Lno_insw_8:	tst	r2, #4
 		beq	.Lno_insw_4
@@ -97,9 +97,9 @@ ENTRY(__raw_readsw)
 
 .Lno_insw_2:	tst	r2, #1
 		ldrne	r3, [r0]
-		strneb	r3, [r1], #1
+		strbne	r3, [r1], #1
 		movne	r3, r3, lsr #8
-		strneb	r3, [r1]
+		strbne	r3, [r1]
 
 		ldmfd	sp!, {r4, r5, r6, pc}
 
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index d9a45e9692ae..5efdd66f5dcd 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -76,8 +76,8 @@ ENTRY(__raw_readsw)
 		pack	r3, r3, ip
 		str	r3, [r1], #4
 
-.Lno_insw_2:	ldrneh	r3, [r0]
-		strneh	r3, [r1]
+.Lno_insw_2:	ldrhne	r3, [r0]
+		strhne	r3, [r1]
 
 		ldmfd	sp!, {r4, r5, pc}
 
@@ -94,7 +94,7 @@ ENTRY(__raw_readsw)
 #endif
 
 .Linsw_noalign:	stmfd	sp!, {r4, lr}
-		ldrccb	ip, [r1, #-1]!
+		ldrbcc	ip, [r1, #-1]!
 		bcc	1f
 
 		ldrh	ip, [r0]
@@ -121,11 +121,11 @@ ENTRY(__raw_readsw)
 
 3:		tst	r2, #1
 		strb	ip, [r1], #1
-		ldrneh	ip, [r0]
+		ldrhne	ip, [r0]
    _BE_ONLY_(	movne	ip, ip, ror #8		)
-		strneb	ip, [r1], #1
+		strbne	ip, [r1], #1
    _LE_ONLY_(	movne	ip, ip, lsr #8		)
    _BE_ONLY_(	movne	ip, ip, lsr #24		)
-		strneb	ip, [r1]
+		strbne	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 a46bbc9b168b..7d2881a2381e 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -36,10 +36,10 @@
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
-		ldrgeb	r3, [r1], #1
-		strgeb	r3, [r0]
-		ldrgtb	r3, [r1], #1
-		strgtb	r3, [r0]
+		ldrbge	r3, [r1], #1
+		strbge	r3, [r0]
+		ldrbgt	r3, [r1], #1
+		strbgt	r3, [r0]
 		subs	r2, r2, ip
 		bne	.Loutsb_aligned
 
@@ -64,7 +64,7 @@ ENTRY(__raw_writesb)
 		bpl	.Loutsb_16_lp
 
 		tst	r2, #15
-		ldmeqfd	sp!, {r4, r5, pc}
+		ldmfdeq	sp!, {r4, r5, pc}
 
 .Loutsb_no_16:	tst	r2, #8
 		beq	.Loutsb_no_8
@@ -80,15 +80,15 @@ ENTRY(__raw_writesb)
 		outword	r3
 
 .Loutsb_no_4:	ands	r2, r2, #3
-		ldmeqfd	sp!, {r4, r5, pc}
+		ldmfdeq	sp!, {r4, r5, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
-		ldrgeb	r3, [r1], #1
-		strgeb	r3, [r0]
-		ldrgtb	r3, [r1]
-		strgtb	r3, [r0]
+		ldrbge	r3, [r1], #1
+		strbge	r3, [r0]
+		ldrbgt	r3, [r1]
+		strbgt	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 4ea2435988c1..7596ac0c90b0 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -28,7 +28,7 @@ ENTRY(__raw_writesl)
 		bpl	1b
 		ldmfd	sp!, {r4, lr}
 2:		movs	r2, r2, lsl #31
-		ldmcsia	r1!, {r3, ip}
+		ldmiacs	r1!, {r3, ip}
 		strcs	r3, [r0, #0]
 		ldrne	r3, [r1, #0]
 		strcs	ip, [r0, #0]
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
index 121789eb6802..cb94b9b49405 100644
--- a/arch/arm/lib/io-writesw-armv3.S
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -79,7 +79,7 @@ ENTRY(__raw_writesw)
 		bpl	.Loutsw_8_lp
 
 		tst	r2, #7
-		ldmeqfd	sp!, {r4, r5, r6, pc}
+		ldmfdeq	sp!, {r4, r5, r6, pc}
 
 .Lno_outsw_8:	tst	r2, #4
 		beq	.Lno_outsw_4
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index 269f90c51ad2..e6645b2f249e 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -61,8 +61,8 @@ ENTRY(__raw_writesw)
 		ldr	r3, [r1], #4
 		outword	r3
 
-.Lno_outsw_2:	ldrneh	r3, [r1]
-		strneh	r3, [r0]
+.Lno_outsw_2:	ldrhne	r3, [r1]
+		strhne	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
 
@@ -95,6 +95,6 @@ ENTRY(__raw_writesw)
 
 		tst	r2, #1
 3:		movne	ip, r3, lsr #8
-		strneh	ip, [r0]
+		strhne	ip, [r0]
 		ret	lr
 ENDPROC(__raw_writesw)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 9397b2e532af..c23f9d9e2970 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -96,7 +96,7 @@ Boston, MA 02111-1307, USA.  */
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	orrhs	\result,   \result,   \curbit,  lsr #3
 	cmp	\dividend, #0			@ Early termination?
-	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movsne	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
 	movne	\divisor,  \divisor, lsr #4
 	bne	1b
 
@@ -182,7 +182,7 @@ Boston, MA 02111-1307, USA.  */
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	cmp	\dividend, #1
 	mov	\divisor, \divisor, lsr #4
-	subges	\order, \order, #4
+	subsge	\order, \order, #4
 	bge	1b
 
 	tst	\order, #3
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 64111bd4440b..4a6997bb4404 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -30,7 +30,7 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
-	ldr\cond\()b \reg, [\ptr], #1
+	ldrb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro str1w ptr reg abort
@@ -42,7 +42,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-	str\cond\()b \reg, [\ptr], #1
+	strb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 69a9d47fc5ab..d70304cb2cd0 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -59,7 +59,7 @@ ENTRY(memmove)
 		blt	5f
 
 	CALGN(	ands	ip, r0, #31		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	bcs	2f			)
 	CALGN(	adr	r4, 6f			)
 	CALGN(	subs	r2, r2, ip		)  @ C is set here
@@ -114,20 +114,20 @@ ENTRY(memmove)
 	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block
 
 8:		movs	r2, r2, lsl #31
-		ldrneb	r3, [r1, #-1]!
-		ldrcsb	r4, [r1, #-1]!
-		ldrcsb	ip, [r1, #-1]
-		strneb	r3, [r0, #-1]!
-		strcsb	r4, [r0, #-1]!
-		strcsb	ip, [r0, #-1]
+		ldrbne	r3, [r1, #-1]!
+		ldrbcs	r4, [r1, #-1]!
+		ldrbcs	ip, [r1, #-1]
+		strbne	r3, [r0, #-1]!
+		strbcs	r4, [r0, #-1]!
+		strbcs	ip, [r0, #-1]
 		ldmfd	sp!, {r0, r4, pc}
 
 9:		cmp	ip, #2
-		ldrgtb	r3, [r1, #-1]!
-		ldrgeb	r4, [r1, #-1]!
+		ldrbgt	r3, [r1, #-1]!
+		ldrbge	r4, [r1, #-1]!
 		ldrb	lr, [r1, #-1]!
-		strgtb	r3, [r0, #-1]!
-		strgeb	r4, [r0, #-1]!
+		strbgt	r3, [r0, #-1]!
+		strbge	r4, [r0, #-1]!
 		subs	r2, r2, ip
 		strb	lr, [r0, #-1]!
 		blt	8b
@@ -150,7 +150,7 @@ ENTRY(memmove)
 		blt	14f
 
 	CALGN(	ands	ip, r0, #31		)
-	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index ed6d35d9cdb5..5593a45e0a8c 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -44,20 +44,20 @@ UNWIND( .save {r8, lr}      )
 	mov	lr, r3
 
 2:	subs	r2, r2, #64
-	stmgeia	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
-	stmgeia	ip!, {r1, r3, r8, lr}
-	stmgeia	ip!, {r1, r3, r8, lr}
-	stmgeia	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
 	bgt	2b
-	ldmeqfd	sp!, {r8, pc}		@ Now <64 bytes to go.
+	ldmfdeq	sp!, {r8, pc}		@ Now <64 bytes to go.
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r2, #32
-	stmneia	ip!, {r1, r3, r8, lr}
-	stmneia	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
 	tst	r2, #16
-	stmneia	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
 	ldmfd	sp!, {r8, lr}
 UNWIND( .fnend              )
 
@@ -87,22 +87,22 @@ UNWIND( .save {r4-r8, lr}      )
 	rsb	r8, r8, #32
 	sub	r2, r2, r8
 	movs	r8, r8, lsl #(32 - 4)
-	stmcsia	ip!, {r4, r5, r6, r7}
-	stmmiia	ip!, {r4, r5}
+	stmiacs	ip!, {r4, r5, r6, r7}
+	stmiami	ip!, {r4, r5}
 	tst	r8, #(1 << 30)
 	mov	r8, r1
 	strne	r1, [ip], #4
 
 3:	subs	r2, r2, #64
-	stmgeia	ip!, {r1, r3-r8, lr}
-	stmgeia	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
 	bgt	3b
-	ldmeqfd	sp!, {r4-r8, pc}
+	ldmfdeq	sp!, {r4-r8, pc}
 
 	tst	r2, #32
-	stmneia	ip!, {r1, r3-r8, lr}
+	stmiane	ip!, {r1, r3-r8, lr}
 	tst	r2, #16
-	stmneia	ip!, {r4-r7}
+	stmiane	ip!, {r4-r7}
 	ldmfd	sp!, {r4-r8, lr}
 UNWIND( .fnend                 )
 
@@ -110,7 +110,7 @@ UNWIND( .fnend                 )
 
 UNWIND( .fnstart            )
 4:	tst	r2, #8
-	stmneia	ip!, {r1, r3}
+	stmiane	ip!, {r1, r3}
 	tst	r2, #4
 	strne	r1, [ip], #4
 /*
@@ -118,17 +118,17 @@ UNWIND( .fnstart            )
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
-	strneb	r1, [ip], #1
-	strneb	r1, [ip], #1
+	strbne	r1, [ip], #1
+	strbne	r1, [ip], #1
 	tst	r2, #1
-	strneb	r1, [ip], #1
+	strbne	r1, [ip], #1
 	ret	lr
 
 6:	subs	r2, r2, #4		@ 1 do we have enough
 	blt	5b			@ 1 bytes to align with?
 	cmp	r3, #2			@ 1
-	strltb	r1, [ip], #1		@ 1
-	strleb	r1, [ip], #1		@ 1
+	strblt	r1, [ip], #1		@ 1
+	strble	r1, [ip], #1		@ 1
 	strb	r1, [ip], #1		@ 1
 	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
 	b	1b
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index 2c40aeab3eaa..c691b901092f 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -14,7 +14,7 @@
 MODULE_LICENSE("GPL");
 
 #ifndef __ARM_NEON__
-#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
 #endif
 
 /*