ARM: 8844/1: use unified assembler in assembly files

Use unified assembler syntax (UAL) in assembly files. Divided
syntax is considered deprecated. This will also allow to build
the kernel using LLVM's integrated assembler.

Signed-off-by: Stefan Agner <[e-mail]>
Acked-by: Nicolas Pitre <[e-mail]>
Signed-off-by: Russell King <[e-mail]>

arch/arm/boot/bootp/init.S

···
  */
 		movne	r10, #0			@ terminator
 		movne	r4, #2			@ Size of this entry (2 words)
-		stmneia	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
+		stmiane	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
 
 /*
  * find the end of the tag list, and then add an INITRD tag on the end.

arch/arm/boot/compressed/ll_char_wr.S

···
 	tst	r1, #7				@ avoid using r7 directly after
 	str	r7, [r0, -r5]!
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow4bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 
···
 	sub	r0, r0, r5			@ avoid ip
 	stmia	r0, {r4, ip}
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow8bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 

arch/arm/include/asm/hardware/entry-macro-iomd.S

···
 		ldr	\tmp, =irq_prio_h
 		teq	\irqstat, #0
 #ifdef IOMD_BASE
-		ldreqb	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
+		ldrbeq	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
 		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
 		teqeq	\irqstat, #0
 		bne	2406f
 #endif
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
 		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
 		teqeq	\irqstat, #0
 #ifdef IOMD_IRQREQC
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQC]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQC]
 		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
 		teqeq	\irqstat, #0
 #endif
 #ifdef IOMD_IRQREQD
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQD]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQD]
 		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
 		teqeq	\irqstat, #0
 #endif
-2406:		ldrneb	\irqnr, [\tmp, \irqstat]	@ get IRQ number
+2406:		ldrbne	\irqnr, [\tmp, \irqstat]	@ get IRQ number
 		.endm
 
 /*

arch/arm/include/debug/tegra.S

···
 
 		.macro	senduart, rd, rx
 		cmp	\rx, #0
-		strneb	\rd, [\rx, #UART_TX << UART_SHIFT]
+		strbne	\rd, [\rx, #UART_TX << UART_SHIFT]
 1001:
 		.endm
 

arch/arm/kernel/debug.S

···
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 1:		teq	r0, #0
-		ldrneb	r1, [r0], #1
+		ldrbne	r1, [r0], #1
 		teqne	r1, #0
 		reteq	lr
 2:		teq     r1, #'\n'

arch/arm/kernel/entry-armv.S

···
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
 	rsbs	r7, r8, #(1 << 8)		@ CP 0 or 1 only
-	movcss	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
+	movscs	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
···
 	smp_dmb	arm
 1:	ldrexd	r0, r1, [r2]			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	eorseq	r3, r1, r5			@ compare with oldval (2)
 	strexdeq r3, r6, r7, [r2]		@ store newval if eq
 	teqeq	r3, #1				@ success?
 	beq	1b				@ if no then retry
···
 	ldmia	r1, {r6, lr}			@ load new val
 1:	ldmia	r2, {r0, r1}			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
-2:	stmeqia	r2, {r6, lr}			@ store newval if eq
+	eorseq	r3, r1, r5			@ compare with oldval (2)
+2:	stmiaeq	r2, {r6, lr}			@ store newval if eq
 	rsbs	r0, r3, #0			@ set return val and C flag
 	ldmfd	sp!, {r4, r5, r6, pc}
 
···
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 #if __LINUX_ARM_ARCH__ < 6
 	bcc	kuser_cmpxchg32_fixup
···
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 	ret	lr
 	.previous

arch/arm/kernel/entry-common.S

···
 		movhs	scno, #0
 		csdb
 #endif
-		stmloia	sp, {r5, r6}		@ shuffle args
+		stmialo	sp, {r5, r6}		@ shuffle args
 		movlo	r0, r1
 		movlo	r1, r2
 		movlo	r2, r3

arch/arm/kernel/entry-header.S

···
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
 #else
···
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
 #endif

arch/arm/lib/clear_user.S

···
 		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)

arch/arm/lib/copy_page.S

···
 	.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)

arch/arm/lib/copy_template.S

···
 
 	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
···
 
 	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			)
 

arch/arm/lib/csumpartial.S

···
 		/* 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
···
 		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
···
 		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
···
 		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)

arch/arm/lib/csumpartialcopygeneric.S

···
 		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

arch/arm/lib/csumpartialcopyuser.S

···
 		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

arch/arm/lib/div64.S

···
  	@ 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
 

arch/arm/lib/floppydma.S

···
 		.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:
···
 		.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:

arch/arm/lib/io-readsb.S

···
 		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
 
···
 		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
···
 		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)

arch/arm/lib/io-readsl.S

···
 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

arch/arm/lib/io-readsw-armv3.S

···
 		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
···
 
 .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}
 

arch/arm/lib/io-readsw-armv4.S

···
 		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}
 
···
 #endif
 
 .Linsw_noalign:	stmfd	sp!, {r4, lr}
-		ldrccb	ip, [r1, #-1]!
+		ldrbcc	ip, [r1, #-1]!
 		bcc	1f
 
 		ldrh	ip, [r0]
···
 
 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)

arch/arm/lib/io-writesb.S

···
 		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
 
···
 		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
···
 		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)

arch/arm/lib/io-writesl.S

···
 		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]

arch/arm/lib/io-writesw-armv3.S

···
 		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

arch/arm/lib/io-writesw-armv4.S

···
 		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}
 
···
 
 		tst	r2, #1
 3:		movne	ip, r3, lsr #8
-		strneh	ip, [r0]
+		strhne	ip, [r0]
 		ret	lr
 ENDPROC(__raw_writesw)

arch/arm/lib/lib1funcs.S

···
 	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
 
···
 	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

arch/arm/lib/memmove.S

···
 		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
···
 	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
···
 		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			)
 

arch/arm/lib/memset.S

···
 	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              )
 
···
 	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                 )
 
···
 
 UNWIND( .fnstart            )
 4:	tst	r2, #8
-	stmneia	ip!, {r1, r3}
+	stmiane	ip!, {r1, r3}
 	tst	r2, #4
 	strne	r1, [ip], #4
 /*
···
  * 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

arch/arm/mach-ks8695/include/mach/entry-macro.S

···
 		moveq	\irqstat, \irqstat, lsr #2
 		addeq	\irqnr, \irqnr, #2
 		tst	\irqstat, #0x01
-		addeqs	\irqnr, \irqnr, #1
+		addseq	\irqnr, \irqnr, #1
 1001:
 	.endm

arch/arm/mach-tegra/reset-handler.S

···
 	mov32	r5, TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET
 	mov	r0, #CPU_NOT_RESETTABLE
 	cmp	r10, #0
-	strneb	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
+	strbne	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
 1:
 #endif
 

arch/arm/mm/cache-v6.S

···
 #endif
 	tst	r1, #D_CACHE_LINE_SIZE - 1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrneb	r2, [r1, #-1]			@ read for ownership
-	strneb	r2, [r1, #-1]			@ write for ownership
+	ldrbne	r2, [r1, #-1]			@ read for ownership
+	strbne	r2, [r1, #-1]			@ write for ownership
 #endif
 	bic	r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
···
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrlob	r2, [r0]			@ read for ownership
-	strlob	r2, [r0]			@ write for ownership
+	ldrblo	r2, [r0]			@ read for ownership
+	strblo	r2, [r0]			@ write for ownership
 #endif
 	blo	1b
 	mov	r0, #0

arch/arm/mm/proc-v7m.S

···
 
 	@ Configure caches (if implemented)
 	teq     r8, #0
-	stmneia	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
+	stmiane	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
 	blne	v7m_invalidate_l1
 	teq     r8, #0			@ re-evalutae condition
-	ldmneia	sp, {r0-r6, lr}
+	ldmiane	sp, {r0-r6, lr}
 
 	@ Configure the System Control Register to ensure 8-byte stack alignment
 	@ Note the STKALIGN bit is either RW or RAO.