Merge commit 'arm/2.6.28-arm' into android-tegra-2.6.29

Conflicts:
	MAINTAINERS
	arch/arm/Kconfig
	arch/arm/Makefile
	arch/arm/boot/compressed/head.S
	arch/arm/common/Makefile
	arch/arm/configs/realview-smp_defconfig
	arch/arm/configs/realview_defconfig
	arch/arm/configs/versatile_defconfig
	arch/arm/include/asm/elf.h
	arch/arm/include/asm/uaccess.h
	arch/arm/kernel/module.c
	arch/arm/kernel/signal.c
	arch/arm/mach-realview/Kconfig
	arch/arm/mach-realview/Makefile
	arch/arm/mach-realview/core.c
	arch/arm/mach-realview/core.h
	arch/arm/mach-realview/include/mach/board-pba8.h
	arch/arm/mach-realview/include/mach/debug-macro.S
	arch/arm/mach-realview/include/mach/hardware.h
	arch/arm/mach-realview/include/mach/irqs.h
	arch/arm/mach-realview/include/mach/memory.h
	arch/arm/mach-realview/include/mach/uncompress.h
	arch/arm/mach-realview/localtimer.c
	arch/arm/mach-realview/platsmp.c
	arch/arm/mach-realview/realview_eb.c
	arch/arm/mach-realview/realview_pb1176.c
	arch/arm/mach-realview/realview_pb11mp.c
	arch/arm/mach-realview/realview_pba8.c
	arch/arm/mm/Kconfig
	arch/arm/mm/copypage-v6.c
	arch/arm/mm/dma-mapping.c
	arch/arm/mm/proc-v7.S
	arch/arm/oprofile/op_model_mpcore.c
	arch/arm/tools/mach-types
	arch/arm/vfp/vfpmodule.c
	drivers/mtd/maps/integrator-flash.c
	drivers/net/smsc911x.c
	drivers/net/smsc911x.h

38 files changed, 354 insertions, 113 deletions

diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index 1154d924080b..b18944b85e4b 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -41,9 +41,12 @@ ENTRY(__aeabi_llsl)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
+	itett	mi
 	movmi	ah, ah, lsl r2
 	movpl	ah, al, lsl r3
-	orrmi	ah, ah, al, lsr ip
+ ARM(	orrmi	ah, ah, al, lsr ip	)
+ THUMB(	lsrmi	r3, al, ip		)
+ THUMB(	orrmi	ah, ah, r3		)
 	mov	al, al, lsl r2
 	mov	pc, lr
 
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index 9f8b35572f8c..0d5ace74dd9d 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -41,9 +41,12 @@ ENTRY(__aeabi_lasr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
+	itett	mi
 	movmi	al, al, lsr r2
 	movpl	al, ah, asr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, asr r2
 	mov	pc, lr
 
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index b0951d0e8b2c..41c4d3561b8f 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -28,7 +28,7 @@ ENTRY(__backtrace)
 
 ENTRY(c_backtrace)
 
-#if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
+#if defined(CONFIG_THUMB2_KERNEL) || !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
 		mov	pc, lr
 ENDPROC(__backtrace)
 ENDPROC(c_backtrace)
@@ -38,7 +38,10 @@ ENDPROC(c_backtrace)
 		beq	no_frame		@ we have no stack frames
 
 		tst	r1, #0x10		@ 26 or 32-bit mode?
-		moveq	mask, #0xfc000003	@ mask for 26-bit
+		itte	eq
+ ARM(		moveq	mask, #0xfc000003	)
+ THUMB(		moveq	mask, #0xfc000000	)
+ THUMB(		orreq	mask, #0x03		)
 		movne	mask, #0		@ mask for 32-bit
 
 1:		stmfd	sp!, {pc}		@ calculate offset of PC stored
@@ -73,6 +76,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 1003:		ldr	r2, [sv_pc, #-4]	@ if stmfd sp!, {args} exists,
 		ldr	r3, .Ldsi+4		@ adjust saved 'pc' back one
 		teq	r3, r2, lsr #10		@ instruction
+		ite	ne
 		subne	r0, sv_pc, #4		@ allow for mov
 		subeq	r0, sv_pc, #8		@ allow for mov + stmia
 
@@ -84,6 +88,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		ldr	r1, [sv_pc, #-4]	@ if stmfd sp!, {args} exists,
 		ldr	r3, .Ldsi+4
 		teq	r3, r1, lsr #10
+		ittt	eq
 		ldreq	r0, [frame, #-8]	@ get sp
 		subeq	r0, r0, #4		@ point at the last arg
 		bleq	.Ldumpstm		@ dump saved registers
@@ -91,6 +96,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 1004:		ldr	r1, [sv_pc, #0]		@ if stmfd sp!, {..., fp, ip, lr, pc}
 		ldr	r3, .Ldsi		@ instruction exists,
 		teq	r3, r1, lsr #10
+		itt	eq
 		subeq	r0, frame, #16
 		bleq	.Ldumpstm		@ dump saved registers
 
@@ -126,10 +132,13 @@ ENDPROC(c_backtrace)
 		mov	reg, #10
 		mov	r7, #0
 1:		mov	r3, #1
-		tst	instr, r3, lsl reg
+ ARM(		tst	instr, r3, lsl reg	)
+ THUMB(		lsl	r3, reg			)
+ THUMB(		tst	instr, r3		)
 		beq	2f
 		add	r7, r7, #1
 		teq	r7, #6
+		itte	eq
 		moveq	r7, #1
 		moveq	r1, #'\n'
 		movne	r1, #' '
@@ -140,6 +149,7 @@ ENDPROC(c_backtrace)
 2:		subs	reg, reg, #1
 		bpl	1b
 		teq	r7, #0
+		itt	ne
 		adrne	r0, .Lcr
 		blne	printk
 		ldmfd	sp!, {instr, reg, stack, r7, pc}
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 2e787d40d599..28c7e4e1ef76 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -5,6 +5,13 @@
 	and	r3, r0, #7		@ Get bit offset
 	add	r1, r1, r0, lsr #3	@ Get byte offset
 	mov	r3, r2, lsl r3
+#ifdef CONFIG_ARM_ERRATA_351422
+	mrc     p15, 0, r0, c0, c0, 5
+	and	r0, r0, #0xf
+	mov	r0, r0, lsl #8
+3:	subs	r0, r0, #1
+	bpl	3b
+#endif
 1:	ldrexb	r2, [r1]
 	\instr	r2, r2, r3
 	strexb	r0, r2, [r1]
@@ -13,18 +20,29 @@
 	mov	pc, lr
 	.endm
 
-	.macro	testop, instr, store
+	.macro	testop, instr, store, cond=al
 	and	r3, r0, #7		@ Get bit offset
 	mov	r2, #1
 	add	r1, r1, r0, lsr #3	@ Get byte offset
 	mov	r3, r2, lsl r3		@ create mask
+#ifdef CONFIG_ARM_ERRATA_351422
+	mrc     p15, 0, r0, c0, c0, 5
+	and	r0, r0, #0xf
+	mov	r0, r0, lsl #8
+3:	subs	r0, r0, #1
+	bpl	3b
+#endif
 1:	ldrexb	r2, [r1]
 	ands	r0, r2, r3		@ save old value of bit
-	\instr	r2, r2, r3			@ toggle bit
+	.ifnc	\cond,al
+	it	\cond
+	.endif
+	\instr	r2, r2, r3		@ toggle bit
 	strexb	ip, r2, [r1]
 	cmp	ip, #0
 	bne	1b
 	cmp	r0, #0
+	it	ne
 	movne	r0, #1
 2:	mov	pc, lr
 	.endm
@@ -49,7 +67,7 @@
  * Note: we can trivially conditionalise the store instruction
  * to avoid dirtying the data cache.
  */
-	.macro	testop, instr, store
+	.macro	testop, instr, store, cond=al
 	add	r1, r1, r0, lsr #3
 	and	r3, r0, #7
 	mov	r0, #1
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 4d6bc71231f3..2147bec77ce4 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -26,21 +26,20 @@ ENTRY(__clear_user)
 		ands	ip, r0, #3
 		beq	1f
 		cmp	ip, #2
-USER(		strbt	r2, [r0], #1)
-USER(		strlebt	r2, [r0], #1)
-USER(		strltbt	r2, [r0], #1)
+		strusr	r2, r0, 1
+		strusr	r2, r0, 1, le
+		strusr	r2, r0, 1, lt
 		rsb	ip, ip, #4
 		sub	r1, r1, ip		@  7  6  5  4  3  2  1
 1:		subs	r1, r1, #8		@ -1 -2 -3 -4 -5 -6 -7
-USER(		strplt	r2, [r0], #4)
-USER(		strplt	r2, [r0], #4)
+		strusr	r2, r0, 4, pl, rept=2
 		bpl	1b
 		adds	r1, r1, #4		@  3  2  1  0 -1 -2 -3
-USER(		strplt	r2, [r0], #4)
+		strusr	r2, r0, 4, pl
 2:		tst	r1, #2			@ 1x 1x 0x 0x 1x 1x 0x
-USER(		strnebt	r2, [r0], #1)
-USER(		strnebt	r2, [r0], #1)
+		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])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 56799a165cc4..9a7a16426428 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -33,11 +33,15 @@
  *	Number of bytes NOT copied.
  */
 
+#ifndef CONFIG_THUMB2_KERNEL
+#define LDR1W_SHIFT	0
+#else
+#define LDR1W_SHIFT	1
+#endif
+#define STR1W_SHIFT	0
+
 	.macro ldr1w ptr reg abort
-100:	ldrt \reg, [\ptr], #4
-	.section __ex_table, "a"
-	.long 100b, \abort
-	.previous
+	ldrusr	\reg, \ptr, 4, abort=\abort
 	.endm
 
 	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
@@ -53,14 +57,11 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
-100:	ldr\cond\()bt \reg, [\ptr], #1
-	.section __ex_table, "a"
-	.long 100b, \abort
-	.previous
+	ldrusr	\reg, \ptr, 1, \cond, abort=\abort
 	.endm
 
 	.macro str1w ptr reg abort
-	str \reg, [\ptr], #4
+	W(str) \reg, [\ptr], #4
 	.endm
 
 	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
@@ -68,6 +69,9 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
+	.ifnc \cond,al
+	it \cond
+	.endif
 	str\cond\()b \reg, [\ptr], #1
 	.endm
 
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 6ae04db1ca4f..1c57a034cadf 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -39,8 +39,10 @@ ENTRY(copy_page)
 		ldmia	r1!, {r3, r4, ip, lr}		@	4
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
+		itt	gt
 		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
 		bgt	1b				@	1
+	PLD(	itt	eq			)
 	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
 	PLD(	beq	2b			)
 		ldmfd	sp!, {r4, pc}			@	3
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 139cce646055..8e8fc03f55bd 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -57,6 +57,13 @@
  *
  *	Restore registers with the values previously saved with the
  *	'preserv' macro. Called upon code termination.
+ *
+ * LDR1W_SHIFT
+ * STR1W_SHIFT
+ *
+ *	Correction to be applied to the "ip" register when branching into
+ *	the ldr1w or str1w instructions (some of these macros may expand to
+ *	than one 32bit instruction in Thumb-2)
  */
 
 
@@ -99,9 +106,16 @@
 
 5:		ands	ip, r2, #28
 		rsb	ip, ip, #32
+#if LDR1W_SHIFT > 0
+		lsl	ip, ip, #LDR1W_SHIFT
+#endif
+		it	ne
 		addne	pc, pc, ip		@ C is always clear here
 		b	7f
-6:		nop
+6:
+		.rept	(1 << LDR1W_SHIFT)
+		W(nop)
+		.endr
 		ldr1w	r1, r3, abort=20f
 		ldr1w	r1, r4, abort=20f
 		ldr1w	r1, r5, abort=20f
@@ -110,9 +124,16 @@
 		ldr1w	r1, r8, abort=20f
 		ldr1w	r1, lr, abort=20f
 
+#if LDR1W_SHIFT < STR1W_SHIFT
+		lsl	ip, ip, #STR1W_SHIFT - LDR1W_SHIFT
+#elif LDR1W_SHIFT > STR1W_SHIFT
+		lsr	ip, ip, #LDR1W_SHIFT - STR1W_SHIFT
+#endif
 		add	pc, pc, ip
 		nop
-		nop
+		.rept	(1 << STR1W_SHIFT)
+		W(nop)
+		.endr
 		str1w	r0, r3, abort=20f
 		str1w	r0, r4, abort=20f
 		str1w	r0, r5, abort=20f
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 22f968bbdffd..dc0fe7391527 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -33,8 +33,15 @@
  *	Number of bytes NOT copied.
  */
 
+#define LDR1W_SHIFT	0
+#ifndef CONFIG_THUMB2_KERNEL
+#define STR1W_SHIFT	0
+#else
+#define STR1W_SHIFT	1
+#endif
+
 	.macro ldr1w ptr reg abort
-	ldr \reg, [\ptr], #4
+	W(ldr) \reg, [\ptr], #4
 	.endm
 
 	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
@@ -46,14 +53,14 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
+	.ifnc \cond,al
+	it \cond
+	.endif
 	ldr\cond\()b \reg, [\ptr], #1
 	.endm
 
 	.macro str1w ptr reg abort
-100:	strt \reg, [\ptr], #4
-	.section __ex_table, "a"
-	.long 100b, \abort
-	.previous
+	strusr	\reg, \ptr, 4, abort=\abort
 	.endm
 
 	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
@@ -68,10 +75,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-100:	str\cond\()bt \reg, [\ptr], #1
-	.section __ex_table, "a"
-	.long 100b, \abort
-	.previous
+	strusr	\reg, \ptr, 1, \cond, abort=\abort
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index 31d3cb34740d..e9a504e4302e 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -39,6 +39,7 @@ td3	.req	lr
 
 		/* we must have at least one byte. */
 		tst	buf, #1			@ odd address?
+		itttt	ne
 		movne	sum, sum, ror #8
 		ldrneb	td0, [buf], #1
 		subne	len, len, #1
@@ -68,25 +69,30 @@ td3	.req	lr
 		bne	.Lless8_wordlp
 
 .Lless8_byte:	tst	len, #1			@ odd number of bytes
+		itt	ne
 		ldrneb	td0, [buf], #1		@ include last byte
 		adcnes	sum, sum, td0, put_byte_0	@ update checksum
 
 .Ldone:		adc	r0, sum, #0		@ collect up the last carry
 		ldr	td0, [sp], #4
 		tst	td0, #1			@ check buffer alignment
+		it	ne
 		movne	r0, r0, ror #8		@ rotate checksum by 8 bits
 		ldr	pc, [sp], #4		@ return
 
 .Lnot_aligned:	tst	buf, #1			@ odd address
+		ittt	ne
 		ldrneb	td0, [buf], #1		@ make even
 		subne	len, len, #1
 		adcnes	sum, sum, td0, put_byte_1	@ update checksum
 
 		tst	buf, #2			@ 32-bit aligned?
 #if __LINUX_ARM_ARCH__ >= 4
+		itt	ne
 		ldrneh	td0, [buf], #2		@ make 32-bit aligned
 		subne	len, len, #2
 #else
+		itttt	ne
 		ldrneb	td0, [buf], #1
 		ldrneb	ip, [buf], #1
 		subne	len, len, #2
@@ -96,6 +102,7 @@ td3	.req	lr
 		orrne	td0, ip, td0, lsl #8
 #endif
 #endif
+		it	ne
 		adcnes	sum, sum, td0		@ update checksum
 		mov	pc, lr
 
@@ -105,10 +112,12 @@ ENTRY(csum_partial)
 		blo	.Lless8			@ 8 bytes to copy.
 
 		tst	buf, #1
+		it	ne
 		movne	sum, sum, ror #8
 
 		adds	sum, sum, #0		@ C = 0
 		tst	buf, #3			@ Test destination alignment
+		it	ne
 		blne	.Lnot_aligned		@ align destination, return here
 
 1:		bics	ip, len, #31
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d620a5f22a09..8e1c141b6524 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -40,6 +40,7 @@ sum	.req	r3
 		adcs	sum, sum, ip, put_byte_1	@ update checksum
 		strb	ip, [dst], #1
 		tst	dst, #2
+		it	eq
 		moveq	pc, lr			@ dst is now 32bit aligned
 
 .Ldst_16bit:	load2b	r8, ip
@@ -94,6 +95,7 @@ FN_ENTRY
 
 		adds	sum, sum, #0		@ C = 0
 		tst	dst, #3			@ Test destination alignment
+		it	ne
 		blne	.Ldst_unaligned		@ align destination, return here
 
 		/*
@@ -147,6 +149,7 @@ FN_ENTRY
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 .Lexit:		tst	len, #1
+		ittt	ne
 		strneb	r5, [dst], #1
 		andne	r5, r5, #255
 		adcnes	sum, sum, r5, put_byte_0
@@ -160,6 +163,7 @@ FN_ENTRY
 .Ldone:		adc	r0, sum, #0
 		ldr	sum, [sp, #0]		@ dst
 		tst	sum, #1
+		it	ne
 		movne	r0, r0, ror #8
 		load_regs
 
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 14677fb4b0c4..152ed83480f7 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -26,50 +26,28 @@
 		.endm
 
 		.macro	load1b,	reg1
-9999:		ldrbt	\reg1, [r0], $1
-		.section __ex_table, "a"
-		.align	3
-		.long	9999b, 6001f
-		.previous
+		ldrusr	\reg1, r0, 1
 		.endm
 
 		.macro	load2b, reg1, reg2
-9999:		ldrbt	\reg1, [r0], $1
-9998:		ldrbt	\reg2, [r0], $1
-		.section __ex_table, "a"
-		.long	9999b, 6001f
-		.long	9998b, 6001f
-		.previous
+		ldrusr	\reg1, r0, 1
+		ldrusr	\reg2, r0, 1
 		.endm
 
 		.macro	load1l, reg1
-9999:		ldrt	\reg1, [r0], $4
-		.section __ex_table, "a"
-		.align	3
-		.long	9999b, 6001f
-		.previous
+		ldrusr	\reg1, r0, 4
 		.endm
 
 		.macro	load2l, reg1, reg2
-9999:		ldrt	\reg1, [r0], $4
-9998:		ldrt	\reg2, [r0], $4
-		.section __ex_table, "a"
-		.long	9999b, 6001f
-		.long	9998b, 6001f
-		.previous
+		ldrusr	\reg1, r0, 4
+		ldrusr	\reg2, r0, 4
 		.endm
 
 		.macro	load4l, reg1, reg2, reg3, reg4
-9999:		ldrt	\reg1, [r0], $4
-9998:		ldrt	\reg2, [r0], $4
-9997:		ldrt	\reg3, [r0], $4
-9996:		ldrt	\reg4, [r0], $4
-		.section __ex_table, "a"
-		.long	9999b, 6001f
-		.long	9998b, 6001f
-		.long	9997b, 6001f
-		.long	9996b, 6001f
-		.previous
+		ldrusr	\reg1, r0, 4
+		ldrusr	\reg2, r0, 4
+		ldrusr	\reg3, r0, 4
+		ldrusr	\reg4, r0, 4
 		.endm
 
 /*
@@ -92,14 +70,15 @@
  */
 		.section .fixup,"ax"
 		.align	4
-6001:		mov	r4, #-EFAULT
+9001:		mov	r4, #-EFAULT
 		ldr	r5, [fp, #4]		@ *err_ptr
 		str	r4, [r5]
 		ldmia	sp, {r1, r2}		@ retrieve dst, len
 		add	r2, r2, r1
 		mov	r0, #0			@ zero the buffer
-6002:		teq	r2, r1
+9002:		teq	r2, r1
+		it	ne
 		strneb	r0, [r1], #1
-		bne	6002b
+		bne	9002b
 		load_regs
 		.previous
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay.S
index 8d6a8762ab88..fcd87ffe2b1d 100644
--- a/arch/arm/lib/delay.S
+++ b/arch/arm/lib/delay.S
@@ -31,6 +31,7 @@ ENTRY(__const_udelay)				@ 0 <= r0 <= 0x7fffff06
 		mov	r2, r2, lsr #10		@ max = 0x00007fff
 		mul	r0, r2, r0		@ max = 2^32-1
 		movs	r0, r0, lsr #6
+		it	eq
 		moveq	pc, lr
 
 /*
@@ -58,6 +59,7 @@ ENTRY(__delay)
 		movls	pc, lr
 		subs	r0, r0, #1
 #endif
+		it	hi
 		bhi	__delay
 		mov	pc, lr
 ENDPROC(__udelay)
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index 1425e789ba86..d02268ac7baf 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -84,8 +84,10 @@ ENTRY(__do_div64)
 	@ The division loop for needed upper bit positions.
  	@ Break out early if dividend reaches 0.
 2:	cmp	xh, yl
+	itt	cs
 	orrcs	yh, yh, ip
 	subcss	xh, xh, yl
+	it	ne
 	movnes	ip, ip, lsr #1
 	mov	yl, yl, lsr #1
 	bne	2b
@@ -93,7 +95,9 @@ ENTRY(__do_div64)
 	@ See if we need to handle lower 32-bit result.
 3:	cmp	xh, #0
 	mov	yl, #0
+	it	eq
 	cmpeq	xl, r4
+	itt	lo
 	movlo	xh, xl
 	movlo	pc, lr
 
@@ -104,7 +108,9 @@ ENTRY(__do_div64)
 4:	movs	xl, xl, lsl #1
 	adcs	xh, xh, xh
 	beq	6f
+	it	cc
 	cmpcc	xh, r4
+	itt	cs
 5:	orrcs	yl, yl, ip
 	subcs	xh, xh, r4
 	movs	ip, ip, lsr #1
@@ -116,6 +122,7 @@ ENTRY(__do_div64)
 	@ Otherwise, if lower part is also null then we are done.
 6:	bcs	5b
 	cmp	xl, #0
+	it	eq
 	moveq	pc, lr
 
 	@ We still have remainer bits in the low part.  Bring them up.
@@ -177,13 +184,16 @@ ENTRY(__do_div64)
 	mov	yh, xh, lsr ip
 	mov	yl, xl, lsr ip
 	rsb	ip, ip, #32
-	orr	yl, yl, xh, lsl ip
+ ARM(	orr	yl, yl, xh, lsl ip	)
+ THUMB(	lsl	xh, xh, ip		)
+ THUMB(	orr	yl, yl, xh		)
 	mov	xh, xl, lsl ip
 	mov	xh, xh, lsr ip
 	mov	pc, lr
 
 	@ eq -> division by 1: obvious enough...
-9:	moveq	yl, xl
+9:	itttt	eq
+	moveq	yl, xl
 	moveq	yh, xh
 	moveq	xh, #0
 	moveq	pc, lr
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 8c4defc4f3c4..1e4cbd4e7be9 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -25,7 +25,10 @@ ENTRY(_find_first_zero_bit_le)
 		teq	r1, #0	
 		beq	3f
 		mov	r2, #0
-1:		ldrb	r3, [r0, r2, lsr #3]
+1:
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		eors	r3, r3, #0xff		@ invert bits
 		bne	.L_found		@ any now set - found zero bit
 		add	r2, r2, #8		@ next bit pointer
@@ -44,7 +47,9 @@ ENTRY(_find_next_zero_bit_le)
 		beq	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
-		ldrb	r3, [r0, r2, lsr #3]
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		eor	r3, r3, #0xff		@ now looking for a 1 bit
 		movs	r3, r3, lsr ip		@ shift off unused bits
 		bne	.L_found
@@ -61,7 +66,10 @@ ENTRY(_find_first_bit_le)
 		teq	r1, #0	
 		beq	3f
 		mov	r2, #0
-1:		ldrb	r3, [r0, r2, lsr #3]
+1:
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		movs	r3, r3
 		bne	.L_found		@ any now set - found zero bit
 		add	r2, r2, #8		@ next bit pointer
@@ -80,7 +88,9 @@ ENTRY(_find_next_bit_le)
 		beq	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
-		ldrb	r3, [r0, r2, lsr #3]
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		movs	r3, r3, lsr ip		@ shift off unused bits
 		bne	.L_found
 		orr	r2, r2, #7		@ if zero, then no bits here
@@ -95,7 +105,9 @@ ENTRY(_find_first_zero_bit_be)
 		beq	3f
 		mov	r2, #0
 1:		eor	r3, r2, #0x18		@ big endian byte ordering
-		ldrb	r3, [r0, r3, lsr #3]
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		eors	r3, r3, #0xff		@ invert bits
 		bne	.L_found		@ any now set - found zero bit
 		add	r2, r2, #8		@ next bit pointer
@@ -111,7 +123,9 @@ ENTRY(_find_next_zero_bit_be)
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
-		ldrb	r3, [r0, r3, lsr #3]
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		eor	r3, r3, #0xff		@ now looking for a 1 bit
 		movs	r3, r3, lsr ip		@ shift off unused bits
 		bne	.L_found
@@ -125,7 +139,9 @@ ENTRY(_find_first_bit_be)
 		beq	3f
 		mov	r2, #0
 1:		eor	r3, r2, #0x18		@ big endian byte ordering
-		ldrb	r3, [r0, r3, lsr #3]
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		movs	r3, r3
 		bne	.L_found		@ any now set - found zero bit
 		add	r2, r2, #8		@ next bit pointer
@@ -141,7 +157,9 @@ ENTRY(_find_next_bit_be)
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
-		ldrb	r3, [r0, r3, lsr #3]
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
 		movs	r3, r3, lsr ip		@ shift off unused bits
 		bne	.L_found
 		orr	r2, r2, #7		@ if zero, then no bits here
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 6763088b7607..3e1b98056c50 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -36,7 +36,10 @@ ENTRY(__get_user_1)
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-2:	ldrbt	r2, [r0], #1
+2:
+ ARM(	ldrbt	r2, [r0], #1	)
+ THUMB(	ldrbt	r2, [r0]	)
+ THUMB(	add	r0, #1		)
 3:	ldrbt	r3, [r0]
 #ifndef __ARMEB__
 	orr	r2, r2, r3, lsl #8
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index 9f4238987fe9..45229e46ed5b 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -12,12 +12,15 @@
 
 .Linsb_align:	rsb	ip, ip, #4
 		cmp	ip, r2
+		it	gt
 		movgt	ip, r2
 		cmp	ip, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
+		itt	ge
 		ldrgeb	r3, [r0]
 		strgeb	r3, [r1], #1
+		itt	gt
 		ldrgtb	r3, [r0]
 		strgtb	r3, [r1], #1
 		subs	r2, r2, ip
@@ -25,6 +28,7 @@
 
 ENTRY(__raw_readsb)
 		teq	r2, #0		@ do we have to check for the zero len?
+		it	eq
 		moveq	pc, lr
 		ands	ip, r1, #3
 		bne	.Linsb_align
@@ -72,6 +76,7 @@ ENTRY(__raw_readsb)
 		bpl	.Linsb_16_lp
 
 		tst	r2, #15
+		it	eq
 		ldmeqfd	sp!, {r4 - r6, pc}
 
 .Linsb_no_16:	tst	r2, #8
@@ -109,13 +114,16 @@ ENTRY(__raw_readsb)
 		str	r3, [r1], #4
 
 .Linsb_no_4:	ands	r2, r2, #3
+		it	eq
 		ldmeqfd	sp!, {r4 - r6, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r0]
 		strb	r3, [r1], #1
+		itt	ge
 		ldrgeb	r3, [r0]
 		strgeb	r3, [r1], #1
+		itt	gt
 		ldrgtb	r3, [r0]
 		strgtb	r3, [r1]
 
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 5fb97e7f9f4b..1f02e66d079c 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -12,6 +12,7 @@
 
 ENTRY(__raw_readsl)
 		teq	r2, #0		@ do we have to check for the zero len?
+		it	eq
 		moveq	pc, lr
 		ands	ip, r1, #3
 		bne	3f
@@ -28,9 +29,11 @@ ENTRY(__raw_readsl)
 		bpl	1b
 		ldmfd	sp!, {r4, lr}
 2:		movs	r2, r2, lsl #31
+		ittt	cs
 		ldrcs	r3, [r0, #0]
 		ldrcs	ip, [r0, #0]
 		stmcsia	r1!, {r3, ip}
+		itt	ne
 		ldrne	r3, [r0, #0]
 		strne	r3, [r1, #0]
 		mov	pc, lr
@@ -48,6 +51,7 @@ ENTRY(__raw_readsl)
 
 4:		subs	r2, r2, #1
 		mov	ip, r3, pull #24
+		itttt	ne
 		ldrne	r3, [r0]
 		orrne	ip, ip, r3, push #8
 		strne	ip, [r1], #4
@@ -56,6 +60,7 @@ ENTRY(__raw_readsl)
 
 5:		subs	r2, r2, #1
 		mov	ip, r3, pull #16
+		itttt	ne
 		ldrne	r3, [r0]
 		orrne	ip, ip, r3, push #16
 		strne	ip, [r1], #4
@@ -64,6 +69,7 @@ ENTRY(__raw_readsl)
 
 6:		subs	r2, r2, #1
 		mov	ip, r3, pull #8
+		itttt	ne
 		ldrne	r3, [r0]
 		orrne	ip, ip, r3, push #24
 		strne	ip, [r1], #4
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index 1f393d42593d..9db32f0541da 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -26,6 +26,7 @@
 
 ENTRY(__raw_readsw)
 		teq	r2, #0
+		it	eq
 		moveq	pc, lr
 		tst	r1, #3
 		bne	.Linsw_align
@@ -76,7 +77,8 @@ ENTRY(__raw_readsw)
 		pack	r3, r3, ip
 		str	r3, [r1], #4
 
-.Lno_insw_2:	ldrneh	r3, [r0]
+.Lno_insw_2:	itt	ne
+		ldrneh	r3, [r0]
 		strneh	r3, [r1]
 
 		ldmfd	sp!, {r4, r5, pc}
@@ -94,6 +96,7 @@ ENTRY(__raw_readsw)
 #endif
 
 .Linsw_noalign:	stmfd	sp!, {r4, lr}
+		it	cc
 		ldrccb	ip, [r1, #-1]!
 		bcc	1f
 
@@ -121,6 +124,7 @@ ENTRY(__raw_readsw)
 
 3:		tst	r2, #1
 		strb	ip, [r1], #1
+		itttt	ne
 		ldrneh	ip, [r0]
    _BE_ONLY_(	movne	ip, ip, ror #8		)
 		strneb	ip, [r1], #1
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
index 68b92f4acaeb..5fad6b0c7f05 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -32,12 +32,15 @@
 
 .Loutsb_align:	rsb	ip, ip, #4
 		cmp	ip, r2
+		it	gt
 		movgt	ip, r2
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
+		itt	ge
 		ldrgeb	r3, [r1], #1
 		strgeb	r3, [r0]
+		itt	gt
 		ldrgtb	r3, [r1], #1
 		strgtb	r3, [r0]
 		subs	r2, r2, ip
@@ -45,6 +48,7 @@
 
 ENTRY(__raw_writesb)
 		teq	r2, #0		@ do we have to check for the zero len?
+		it	eq
 		moveq	pc, lr
 		ands	ip, r1, #3
 		bne	.Loutsb_align
@@ -64,6 +68,7 @@ ENTRY(__raw_writesb)
 		bpl	.Loutsb_16_lp
 
 		tst	r2, #15
+		it	eq
 		ldmeqfd	sp!, {r4, r5, pc}
 
 .Loutsb_no_16:	tst	r2, #8
@@ -80,13 +85,16 @@ ENTRY(__raw_writesb)
 		outword	r3
 
 .Loutsb_no_4:	ands	r2, r2, #3
+		it	eq
 		ldmeqfd	sp!, {r4, r5, pc}
 
 		cmp	r2, #2
 		ldrb	r3, [r1], #1
 		strb	r3, [r0]
+		itt	ge
 		ldrgeb	r3, [r1], #1
 		strgeb	r3, [r0]
+		itt	gt
 		ldrgtb	r3, [r1]
 		strgtb	r3, [r0]
 
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 8d3b7813725c..ced1d9169090 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -12,6 +12,7 @@
 
 ENTRY(__raw_writesl)
 		teq	r2, #0		@ do we have to check for the zero len?
+		it	eq
 		moveq	pc, lr
 		ands	ip, r1, #3
 		bne	3f
@@ -28,10 +29,14 @@ ENTRY(__raw_writesl)
 		bpl	1b
 		ldmfd	sp!, {r4, lr}
 2:		movs	r2, r2, lsl #31
+		itt	cs
 		ldmcsia	r1!, {r3, ip}
 		strcs	r3, [r0, #0]
+		it	ne
 		ldrne	r3, [r1, #0]
+		it	cs
 		strcs	ip, [r0, #0]
+		it	ne
 		strne	r3, [r0, #0]
 		mov	pc, lr
 
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index d6585612c86b..bb8530310ff3 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -31,6 +31,7 @@
 
 ENTRY(__raw_writesw)
 		teq	r2, #0
+		it	eq
 		moveq	pc, lr
 		ands	r3, r1, #3
 		bne	.Loutsw_align
@@ -61,7 +62,8 @@ ENTRY(__raw_writesw)
 		ldr	r3, [r1], #4
 		outword	r3
 
-.Lno_outsw_2:	ldrneh	r3, [r1]
+.Lno_outsw_2:	itt	ne
+		ldrneh	r3, [r1]
 		strneh	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
@@ -75,7 +77,11 @@ ENTRY(__raw_writesw)
 #endif
 
 .Loutsw_noalign:
-		ldr	r3, [r1, -r3]!
+ ARM(		ldr	r3, [r1, -r3]!	)
+ THUMB(		rsb	r3, r3, #0	)
+ THUMB(		ldr	r3, [r1, r3]	)
+ THUMB(		sub	r1, r3		)
+		it	cs
 		subcs	r2, r2, #1
 		bcs	2f
 		subs	r2, r2, #2
@@ -91,7 +97,8 @@ ENTRY(__raw_writesw)
 		bpl	1b
 
 		tst	r2, #1
-3:		movne	ip, r3, lsr #8
+3:		itt	ne
+		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 67964bcfc854..1eb73e769c6c 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -56,6 +56,7 @@ Boston, MA 02111-1307, USA.  */
 	@ at the left end of each 4 bit nibbles in the division loop
 	@ to save one loop in most cases.
 	tst	\divisor, #0xe0000000
+	itte	eq
 	moveq	\divisor, \divisor, lsl #3
 	moveq	\curbit, #8
 	movne	\curbit, #1
@@ -65,6 +66,7 @@ Boston, MA 02111-1307, USA.  */
 	@ division loop.  Continue shifting until the divisor is 
 	@ larger than the dividend.
 1:	cmp	\divisor, #0x10000000
+	ittt	lo
 	cmplo	\divisor, \dividend
 	movlo	\divisor, \divisor, lsl #4
 	movlo	\curbit, \curbit, lsl #4
@@ -73,6 +75,7 @@ Boston, MA 02111-1307, USA.  */
 	@ For very big divisors, we must shift it a bit at a time, or
 	@ we will be in danger of overflowing.
 1:	cmp	\divisor, #0x80000000
+	ittt	lo
 	cmplo	\divisor, \dividend
 	movlo	\divisor, \divisor, lsl #1
 	movlo	\curbit, \curbit, lsl #1
@@ -84,19 +87,25 @@ Boston, MA 02111-1307, USA.  */
 
 	@ Division loop
 1:	cmp	\dividend, \divisor
+	itt	hs
 	subhs	\dividend, \dividend, \divisor
 	orrhs	\result,   \result,   \curbit
 	cmp	\dividend, \divisor,  lsr #1
+	itt	hs
 	subhs	\dividend, \dividend, \divisor, lsr #1
 	orrhs	\result,   \result,   \curbit,  lsr #1
 	cmp	\dividend, \divisor,  lsr #2
+	itt	hs
 	subhs	\dividend, \dividend, \divisor, lsr #2
 	orrhs	\result,   \result,   \curbit,  lsr #2
 	cmp	\dividend, \divisor,  lsr #3
+	itt	hs
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	orrhs	\result,   \result,   \curbit,  lsr #3
 	cmp	\dividend, #0			@ Early termination?
+	it	ne
 	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	it	ne
 	movne	\divisor,  \divisor, lsr #4
 	bne	1b
 
@@ -113,19 +122,24 @@ Boston, MA 02111-1307, USA.  */
 #else
 
 	cmp	\divisor, #(1 << 16)
+	itt	hs
 	movhs	\divisor, \divisor, lsr #16
 	movhs	\order, #16
+	it	lo
 	movlo	\order, #0
 
 	cmp	\divisor, #(1 << 8)
+	itt	hs
 	movhs	\divisor, \divisor, lsr #8
 	addhs	\order, \order, #8
 
 	cmp	\divisor, #(1 << 4)
+	itt	hs
 	movhs	\divisor, \divisor, lsr #4
 	addhs	\order, \order, #4
 
 	cmp	\divisor, #(1 << 2)
+	ite	hi
 	addhi	\order, \order, #3
 	addls	\order, \order, \divisor, lsr #1
 
@@ -152,6 +166,7 @@ Boston, MA 02111-1307, USA.  */
 	@ division loop.  Continue shifting until the divisor is 
 	@ larger than the dividend.
 1:	cmp	\divisor, #0x10000000
+	ittt	lo
 	cmplo	\divisor, \dividend
 	movlo	\divisor, \divisor, lsl #4
 	addlo	\order, \order, #4
@@ -160,6 +175,7 @@ Boston, MA 02111-1307, USA.  */
 	@ For very big divisors, we must shift it a bit at a time, or
 	@ we will be in danger of overflowing.
 1:	cmp	\divisor, #0x80000000
+	ittt	lo
 	cmplo	\divisor, \dividend
 	movlo	\divisor, \divisor, lsl #1
 	addlo	\order, \order, #1
@@ -173,19 +189,25 @@ Boston, MA 02111-1307, USA.  */
 	blt	2f
 
 1:	cmp	\dividend, \divisor
+	it	hs
 	subhs	\dividend, \dividend, \divisor
 	cmp	\dividend, \divisor,  lsr #1
+	it	hs
 	subhs	\dividend, \dividend, \divisor, lsr #1
 	cmp	\dividend, \divisor,  lsr #2
+	it	hs
 	subhs	\dividend, \dividend, \divisor, lsr #2
 	cmp	\dividend, \divisor,  lsr #3
+	it	hs
 	subhs	\dividend, \dividend, \divisor, lsr #3
 	cmp	\dividend, #1
 	mov	\divisor, \divisor, lsr #4
+	it	ge
 	subges	\order, \order, #4
 	bge	1b
 
 	tst	\order, #3
+	it	ne
 	teqne	\dividend, #0
 	beq	5f
 
@@ -194,12 +216,15 @@ Boston, MA 02111-1307, USA.  */
 	blt	4f
 	beq	3f
 	cmp	\dividend, \divisor
+	it	hs
 	subhs	\dividend, \dividend, \divisor
 	mov	\divisor,  \divisor,  lsr #1
 3:	cmp	\dividend, \divisor
+	it	hs
 	subhs	\dividend, \dividend, \divisor
 	mov	\divisor,  \divisor,  lsr #1
 4:	cmp	\dividend, \divisor
+	it	hs
 	subhs	\dividend, \dividend, \divisor
 5:
 .endm
@@ -209,6 +234,7 @@ ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
 
 	subs	r2, r1, #1
+	it	eq
 	moveq	pc, lr
 	bcc	Ldiv0
 	cmp	r0, r1
@@ -221,7 +247,8 @@ ENTRY(__aeabi_uidiv)
 	mov	r0, r2
 	mov	pc, lr
 
-11:	moveq	r0, #1
+11:	ite	eq
+	moveq	r0, #1
 	movne	r0, #0
 	mov	pc, lr
 
@@ -237,10 +264,14 @@ ENTRY(__umodsi3)
 
 	subs	r2, r1, #1			@ compare divisor with 1
 	bcc	Ldiv0
+	ite	ne
 	cmpne	r0, r1				@ compare dividend with divisor
 	moveq   r0, #0
+	it	hi
 	tsthi	r1, r2				@ see if divisor is power of 2
+	it	eq
 	andeq	r0, r0, r2
+	it	ls
 	movls	pc, lr
 
 	ARM_MOD_BODY r0, r1, r2, r3
@@ -255,10 +286,12 @@ ENTRY(__aeabi_idiv)
 	cmp	r1, #0
 	eor	ip, r0, r1			@ save the sign of the result.
 	beq	Ldiv0
+	it	mi
 	rsbmi	r1, r1, #0			@ loops below use unsigned.
 	subs	r2, r1, #1			@ division by 1 or -1 ?
 	beq	10f
 	movs	r3, r0
+	it	mi
 	rsbmi	r3, r0, #0			@ positive dividend value
 	cmp	r3, r1
 	bls	11f
@@ -268,14 +301,18 @@ ENTRY(__aeabi_idiv)
 	ARM_DIV_BODY r3, r1, r0, r2
 
 	cmp	ip, #0
+	it	mi
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
 10:	teq	ip, r0				@ same sign ?
+	it	mi
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
-11:	movlo	r0, #0
+11:	it	lo
+	movlo	r0, #0
+	itt	eq
 	moveq	r0, ip, asr #31
 	orreq	r0, r0, #1
 	mov	pc, lr
@@ -284,6 +321,7 @@ ENTRY(__aeabi_idiv)
 
 	cmp	ip, #0
 	mov	r0, r3, lsr r2
+	it	mi
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
@@ -294,19 +332,25 @@ ENTRY(__modsi3)
 
 	cmp	r1, #0
 	beq	Ldiv0
+	it	mi
 	rsbmi	r1, r1, #0			@ loops below use unsigned.
 	movs	ip, r0				@ preserve sign of dividend
+	it	mi
 	rsbmi	r0, r0, #0			@ if negative make positive
 	subs	r2, r1, #1			@ compare divisor with 1
+	ite	ne
 	cmpne	r0, r1				@ compare dividend with divisor
 	moveq	r0, #0
+	it	hi
 	tsthi	r1, r2				@ see if divisor is power of 2
+	it	eq
 	andeq	r0, r0, r2
 	bls	10f
 
 	ARM_MOD_BODY r0, r1, r2, r3
 
 10:	cmp	ip, #0
+	it	mi
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index 99ea338bf87c..57db3a265e5b 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -41,9 +41,12 @@ ENTRY(__aeabi_llsr)
 
 	subs	r3, r2, #32
 	rsb	ip, r2, #32
+	itett	mi
 	movmi	al, al, lsr r2
 	movpl	al, ah, lsr r3
-	orrmi	al, al, ah, lsl ip
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, lsr r2
 	mov	pc, lr
 
diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S
index 1da86991d700..0d1d596ad8cd 100644
--- a/arch/arm/lib/memchr.S
+++ b/arch/arm/lib/memchr.S
@@ -21,6 +21,7 @@ ENTRY(memchr)
 	teq	r3, r1
 	bne	1b
 	sub	r0, r0, #1
-2:	movne	r0, #0
+2:	it	ne
+	movne	r0, #0
 	mov	pc, lr
 ENDPROC(memchr)
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index e0d002641d3f..c7a810dee294 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -13,8 +13,11 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
+#define LDR1W_SHIFT	0
+#define STR1W_SHIFT	0
+
 	.macro ldr1w ptr reg abort
-	ldr \reg, [\ptr], #4
+	W(ldr) \reg, [\ptr], #4
 	.endm
 
 	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
@@ -26,11 +29,16 @@
 	.endm
 
 	.macro ldr1b ptr reg cond=al abort
+	.ifnc \cond,al
+	it \cond
 	ldr\cond\()b \reg, [\ptr], #1
+	.else
+	ldrb \reg, [\ptr], #1
+	.endif
 	.endm
 
 	.macro str1w ptr reg abort
-	str \reg, [\ptr], #4
+	W(str) \reg, [\ptr], #4
 	.endm
 
 	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
@@ -38,7 +46,12 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
+	.ifnc \cond,al
+	it \cond
 	str\cond\()b \reg, [\ptr], #1
+	.else
+	strb \reg, [\ptr], #1
+	.endif
 	.endm
 
 	.macro enter reg1 reg2
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 12549187088c..191a5dc41596 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -29,7 +29,9 @@
 ENTRY(memmove)
 
 		subs	ip, r0, r1
+		it	hi
 		cmphi	r2, ip
+		it	ls
 		bls	memcpy
 
 		stmfd	sp!, {r0, r4, lr}
@@ -72,46 +74,55 @@ ENTRY(memmove)
 
 5:		ands	ip, r2, #28
 		rsb	ip, ip, #32
+		it	ne
 		addne	pc, pc, ip		@ C is always clear here
 		b	7f
 6:		nop
-		ldr	r3, [r1, #-4]!
-		ldr	r4, [r1, #-4]!
-		ldr	r5, [r1, #-4]!
-		ldr	r6, [r1, #-4]!
-		ldr	r7, [r1, #-4]!
-		ldr	r8, [r1, #-4]!
-		ldr	lr, [r1, #-4]!
+		W(ldr)	r3, [r1, #-4]!
+		W(ldr)	r4, [r1, #-4]!
+		W(ldr)	r5, [r1, #-4]!
+		W(ldr)	r6, [r1, #-4]!
+		W(ldr)	r7, [r1, #-4]!
+		W(ldr)	r8, [r1, #-4]!
+		W(ldr)	lr, [r1, #-4]!
 
 		add	pc, pc, ip
 		nop
 		nop
-		str	r3, [r0, #-4]!
-		str	r4, [r0, #-4]!
-		str	r5, [r0, #-4]!
-		str	r6, [r0, #-4]!
-		str	r7, [r0, #-4]!
-		str	r8, [r0, #-4]!
-		str	lr, [r0, #-4]!
+		W(str)	r3, [r0, #-4]!
+		W(str)	r4, [r0, #-4]!
+		W(str)	r5, [r0, #-4]!
+		W(str)	r6, [r0, #-4]!
+		W(str)	r7, [r0, #-4]!
+		W(str)	r8, [r0, #-4]!
+		W(str)	lr, [r0, #-4]!
 
 	CALGN(	bcs	2b			)
 
 7:		ldmfd	sp!, {r5 - r8}
 
 8:		movs	r2, r2, lsl #31
+		it	ne
 		ldrneb	r3, [r1, #-1]!
+		itt	cs
 		ldrcsb	r4, [r1, #-1]!
 		ldrcsb	ip, [r1, #-1]
+		it	ne
 		strneb	r3, [r0, #-1]!
+		itt	cs
 		strcsb	r4, [r0, #-1]!
 		strcsb	ip, [r0, #-1]
 		ldmfd	sp!, {r0, r4, pc}
 
 9:		cmp	ip, #2
+		it	gt
 		ldrgtb	r3, [r1, #-1]!
+		it	ge
 		ldrgeb	r4, [r1, #-1]!
 		ldrb	lr, [r1, #-1]!
+		it	gt
 		strgtb	r3, [r0, #-1]!
+		it	ge
 		strgeb	r4, [r0, #-1]!
 		subs	r2, r2, ip
 		strb	lr, [r0, #-1]!
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 650d5923ab83..5e1253d4df5c 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -19,7 +19,9 @@
 1:	subs	r2, r2, #4		@ 1 do we have enough
 	blt	5f			@ 1 bytes to align with?
 	cmp	r3, #2			@ 1
+	it	lt
 	strltb	r1, [r0], #1		@ 1
+	it	le
 	strleb	r1, [r0], #1		@ 1
 	strb	r1, [r0], #1		@ 1
 	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
@@ -51,19 +53,23 @@ ENTRY(memset)
 	mov	lr, r1
 
 2:	subs	r2, r2, #64
+	itttt	ge
 	stmgeia	r0!, {r1, r3, ip, lr}	@ 64 bytes at a time.
 	stmgeia	r0!, {r1, r3, ip, lr}
 	stmgeia	r0!, {r1, r3, ip, lr}
 	stmgeia	r0!, {r1, r3, ip, lr}
 	bgt	2b
+	it	eq
 	ldmeqfd	sp!, {pc}		@ Now <64 bytes to go.
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r2, #32
+	itt	ne
 	stmneia	r0!, {r1, r3, ip, lr}
 	stmneia	r0!, {r1, r3, ip, lr}
 	tst	r2, #16
+	it	ne
 	stmneia	r0!, {r1, r3, ip, lr}
 	ldr	lr, [sp], #4
 
@@ -111,17 +117,21 @@ ENTRY(memset)
 #endif
 
 4:	tst	r2, #8
+	it	ne
 	stmneia	r0!, {r1, r3}
 	tst	r2, #4
+	it	ne
 	strne	r1, [r0], #4
 /*
  * When we get here, we've got less than 4 bytes to zero.  We
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
+	itt	ne
 	strneb	r1, [r0], #1
 	strneb	r1, [r0], #1
 	tst	r2, #1
+	it	ne
 	strneb	r1, [r0], #1
 	mov	pc, lr
 ENDPROC(memset)
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
index 3fbdef5f802a..a0e319a4c03f 100644
--- a/arch/arm/lib/memzero.S
+++ b/arch/arm/lib/memzero.S
@@ -21,7 +21,9 @@
 1:	subs	r1, r1, #4		@ 1 do we have enough
 	blt	5f			@ 1 bytes to align with?
 	cmp	r3, #2			@ 1
+	it	lt
 	strltb	r2, [r0], #1		@ 1
+	it	le
 	strleb	r2, [r0], #1		@ 1
 	strb	r2, [r0], #1		@ 1
 	add	r1, r1, r3		@ 1 (r1 = r1 - (4 - r3))
@@ -51,19 +53,23 @@ ENTRY(__memzero)
 	mov	lr, r2			@ 1
 
 3:	subs	r1, r1, #64		@ 1 write 32 bytes out per loop
+	itttt	ge
 	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
 	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
 	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
 	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
 	bgt	3b			@ 1
+	it	eq
 	ldmeqfd	sp!, {pc}		@ 1/2 quick exit
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r1, #32			@ 1
+	itt	ne
 	stmneia	r0!, {r2, r3, ip, lr}	@ 4
 	stmneia	r0!, {r2, r3, ip, lr}	@ 4
 	tst	r1, #16			@ 1 16 bytes or more?
+	it	ne
 	stmneia	r0!, {r2, r3, ip, lr}	@ 4
 	ldr	lr, [sp], #4		@ 1
 
@@ -109,17 +115,21 @@ ENTRY(__memzero)
 #endif
 
 4:	tst	r1, #8			@ 1 8 bytes or more?
+	it	ne
 	stmneia	r0!, {r2, r3}		@ 2
 	tst	r1, #4			@ 1 4 bytes or more?
+	it	ne
 	strne	r2, [r0], #4		@ 1
 /*
  * When we get here, we've got less than 4 bytes to zero.  We
  * may have an unaligned pointer as well.
  */
 5:	tst	r1, #2			@ 1 2 bytes or more?
+	itt	ne
 	strneb	r2, [r0], #1		@ 1
 	strneb	r2, [r0], #1		@ 1
 	tst	r1, #1			@ 1 a byte left over
+	it	ne
 	strneb	r2, [r0], #1		@ 1
 	mov	pc, lr			@ 1
 ENDPROC(__memzero)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 864f3c1c4f18..4d9dc1a526ee 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -38,10 +38,16 @@ ENDPROC(__put_user_1)
 ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
 #ifndef __ARMEB__
-2:	strbt	r2, [r0], #1
+2:
+ ARM(	strbt	r2, [r0], #1	)
+ THUMB(	strbt	r2, [r0]	)
+ THUMB(	add	r0, #1		)
 3:	strbt	ip, [r0]
 #else
-2:	strbt	ip, [r0], #1
+2:
+ ARM(	strbt	ip, [r0], #1	)
+ THUMB(	strbt	ip, [r0]	)
+ THUMB(	add	r0, #1		)
 3:	strbt	r2, [r0]
 #endif
 	mov	r0, #0
@@ -55,7 +61,10 @@ ENTRY(__put_user_4)
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
-5:	strt	r2, [r0], #4
+5:
+ ARM(	strt	r2, [r0], #4	)
+ THUMB(	strt	r2, [r0]	)
+ THUMB(	add	r0, #4		)
 6:	strt	r3, [r0]
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/sha1.S b/arch/arm/lib/sha1.S
index a16fb208c841..09b548cac1a4 100644
--- a/arch/arm/lib/sha1.S
+++ b/arch/arm/lib/sha1.S
@@ -187,6 +187,7 @@ ENTRY(sha_transform)
 
 ENDPROC(sha_transform)
 
+	.align	2
 .L_sha_K:
 	.word	0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
 
@@ -195,6 +196,7 @@ ENDPROC(sha_transform)
  * void sha_init(__u32 *buf)
  */
 
+	.align	2
 .L_sha_initial_digest:
 	.word	0x67452301, 0xefcdab89, 0x98badcfe, 0x10325476, 0xc3d2e1f0
 
diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S
index d8f2a1c1aea4..fd4014e54e37 100644
--- a/arch/arm/lib/strchr.S
+++ b/arch/arm/lib/strchr.S
@@ -18,9 +18,11 @@ ENTRY(strchr)
 		and	r1, r1, #0xff
 1:		ldrb	r2, [r0], #1
 		teq	r2, r1
+		it	ne
 		teqne	r2, #0
 		bne	1b
 		teq	r2, r1
+		ite	ne
 		movne	r0, #0
 		subeq	r0, r0, #1
 		mov	pc, lr
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
index 330373c26dd9..1c9814f346c6 100644
--- a/arch/arm/lib/strncpy_from_user.S
+++ b/arch/arm/lib/strncpy_from_user.S
@@ -23,7 +23,7 @@
 ENTRY(__strncpy_from_user)
 	mov	ip, r1
 1:	subs	r2, r2, #1
-USER(	ldrplbt	r3, [r1], #1)
+	ldrusr	r3, r1, 1, pl
 	bmi	2f
 	strb	r3, [r0], #1
 	teq	r3, #0
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
index 90bb9d020836..7855b2906659 100644
--- a/arch/arm/lib/strnlen_user.S
+++ b/arch/arm/lib/strnlen_user.S
@@ -23,7 +23,7 @@
 ENTRY(__strnlen_user)
 	mov	r2, r0
 1:
-USER(	ldrbt	r3, [r0], #1)
+	ldrusr	r3, r0, 1
 	teq	r3, #0
 	beq	2f
 	subs	r1, r1, #1
diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S
index 302f20cd2423..d7a9440de6b8 100644
--- a/arch/arm/lib/strrchr.S
+++ b/arch/arm/lib/strrchr.S
@@ -18,6 +18,7 @@ ENTRY(strrchr)
 		mov	r3, #0
 1:		ldrb	r2, [r0], #1
 		teq	r2, r1
+		it	eq
 		subeq	r3, r0, #1
 		teq	r2, #0
 		bne	1b
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 543d7094d18e..df66c76e8b29 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -15,6 +15,6 @@
 ENTRY(_test_and_clear_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_clear_bit_le)
-	testop	bicne, strneb
+	testop	bicne, strneb, ne
 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 0b3f390401ce..3938bdf446a6 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -15,6 +15,6 @@
 ENTRY(_test_and_set_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_set_bit_le)
-	testop	orreq, streqb
+	testop	orreq, streqb, eq
 ENDPROC(_test_and_set_bit_be)
 ENDPROC(_test_and_set_bit_le)
diff --git a/arch/arm/lib/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S
index f0df6a91db04..503288955242 100644
--- a/arch/arm/lib/ucmpdi2.S
+++ b/arch/arm/lib/ucmpdi2.S
@@ -27,9 +27,13 @@
 ENTRY(__ucmpdi2)
 
 	cmp	xh, yh
+	it	eq
 	cmpeq	xl, yl
+	it	lo
 	movlo	r0, #0
+	it	eq
 	moveq	r0, #1
+	it	hi
 	movhi	r0, #2
 	mov	pc, lr
 
@@ -40,9 +44,13 @@ ENDPROC(__ucmpdi2)
 ENTRY(__aeabi_ulcmp)
 
 	cmp	xh, yh
+	it	eq
 	cmpeq	xl, yl
+	it	lo
 	movlo	r0, #-1
+	it	eq
 	moveq	r0, #0
+	it	hi
 	movhi	r0, #1
 	mov	pc, lr