Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

25 files changed, 252 insertions, 188 deletions

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 030ba72..59ff42d 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -41,7 +41,6 @@ else
 endif
 
 lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
-lib-$(CONFIG_ARCH_L7200)	+= io-acorn.o
 lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index 1154d92..638deb1 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -43,7 +43,9 @@ ENTRY(__aeabi_llsl)
 	rsb	ip, r2, #32
 	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 9f8b355..015e8aa5 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -43,7 +43,9 @@ ENTRY(__aeabi_lasr)
 	rsb	ip, r2, #32
 	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 b0951d0..a673297 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -38,7 +38,9 @@ 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
+ 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
@@ -108,13 +110,13 @@ no_frame:	ldmfd	sp!, {r4 - r8, pc}
 ENDPROC(__backtrace)
 ENDPROC(c_backtrace)
 		
-		.section __ex_table,"a"
+		.pushsection __ex_table,"a"
 		.align	3
 		.long	1001b, 1006b
 		.long	1002b, 1006b
 		.long	1003b, 1006b
 		.long	1004b, 1006b
-		.previous
+		.popsection
 
 #define instr r4
 #define reg   r5
@@ -126,7 +128,9 @@ 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
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index c7f2627..d422529 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -60,8 +60,8 @@
 	tst	r2, r0, lsl r3
 	\instr	r2, r2, r0, lsl r3
 	\store	r2, [r1]
-	restore_irqs ip
 	moveq	r0, #0
+	restore_irqs ip
 	mov	pc, lr
 	.endm
 #endif
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 844f567..14a0d98 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -27,28 +27,28 @@ WEAK(__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}
 ENDPROC(__clear_user)
+ENDPROC(__clear_user_std)
 
-		.section .fixup,"ax"
+		.pushsection .fixup,"ax"
 		.align	0
 9001:		ldmfd	sp!, {r0, pc}
-		.previous
+		.popsection
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 56799a1..66a477a 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
@@ -89,7 +90,7 @@ ENTRY(__copy_from_user)
 
 ENDPROC(__copy_from_user)
 
-	.section .fixup,"ax"
+	.pushsection .fixup,"ax"
 	.align 0
 	copy_abort_preamble
 	ldmfd	sp!, {r1, r2}
@@ -99,5 +100,5 @@ ENDPROC(__copy_from_user)
 	bl	__memzero
 	ldr	r0, [sp], #4
 	copy_abort_end
-	.previous
+	.popsection
 
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 6ae04db..6ee2f67 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -12,8 +12,9 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 
-#define COPY_COUNT (PAGE_SZ/64 PLD( -1 ))
+#define COPY_COUNT (PAGE_SZ / (2 * L1_CACHE_BYTES) PLD( -1 ))
 
 		.text
 		.align	5
@@ -26,17 +27,16 @@
 ENTRY(copy_page)
 		stmfd	sp!, {r4, lr}			@	2
 	PLD(	pld	[r1, #0]		)
-	PLD(	pld	[r1, #32]		)
+	PLD(	pld	[r1, #L1_CACHE_BYTES]		)
 		mov	r2, #COPY_COUNT			@	1
 		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-1:	PLD(	pld	[r1, #64]		)
-	PLD(	pld	[r1, #96]		)
-2:		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
+1:	PLD(	pld	[r1, #2 * L1_CACHE_BYTES])
+	PLD(	pld	[r1, #3 * L1_CACHE_BYTES])
+2:
+	.rept	(2 * L1_CACHE_BYTES / 16 - 1)
 		stmia	r0!, {r3, r4, ip, lr}		@	4
 		ldmia	r1!, {r3, r4, ip, lr}		@	4
+	.endr
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
 		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 139cce6..805e3f8 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 +106,15 @@
 
 5:		ands	ip, r2, #28
 		rsb	ip, ip, #32
+#if LDR1W_SHIFT > 0
+		lsl	ip, ip, #LDR1W_SHIFT
+#endif
 		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 +123,16 @@
 		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 878820f..d066df6 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
@@ -50,10 +57,7 @@
 	.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 +72,7 @@
 	.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
@@ -92,13 +93,14 @@ WEAK(__copy_to_user)
 #include "copy_template.S"
 
 ENDPROC(__copy_to_user)
+ENDPROC(__copy_to_user_std)
 
-	.section .fixup,"ax"
+	.pushsection .fixup,"ax"
 	.align 0
 	copy_abort_preamble
 	ldmfd	sp!, {r1, r2, r3}
 	sub	r0, r0, r1
 	rsb	r0, r0, r2
 	copy_abort_end
-	.previous
+	.popsection
 
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 14677fb..7d08b43 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
 
 /*
@@ -90,16 +68,16 @@
  * so properly, we would have to add in whatever registers were loaded before
  * the fault, which, with the current asm above is not predictable.
  */
-		.section .fixup,"ax"
+		.pushsection .fixup,"ax"
 		.align	4
-6001:		mov	r4, #-EFAULT
-		ldr	r5, [fp, #4]		@ *err_ptr
+9001:		mov	r4, #-EFAULT
+		ldr	r5, [sp, #8*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
 		strneb	r0, [r1], #1
-		bne	6002b
+		bne	9002b
 		load_regs
-		.previous
+		.popsection
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index 1425e78..faa7748 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -177,7 +177,9 @@ 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
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 8c4defc..64f6bc1 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
@@ -156,8 +174,8 @@ ENDPROC(_find_next_bit_be)
  */
 .L_found:
 #if __LINUX_ARM_ARCH__ >= 5
-		rsb	r1, r3, #0
-		and	r3, r3, r1
+		rsb	r0, r3, #0
+		and	r3, r3, r0
 		clz	r3, r3
 		rsb	r3, r3, #31
 		add	r0, r2, r3
@@ -172,5 +190,7 @@ ENDPROC(_find_next_bit_be)
 		addeq	r2, r2, #1
 		mov	r0, r2
 #endif
+		cmp	r1, r0			@ Clamp to maxbit
+		movlo	r0, r1
 		mov	pc, lr
 
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 6763088..1b049cd 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -28,16 +28,22 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__get_user_1)
-1:	ldrbt	r2, [r0]
+1:	T(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-2:	ldrbt	r2, [r0], #1
-3:	ldrbt	r3, [r0]
+#ifdef CONFIG_THUMB2_KERNEL
+2:	T(ldrb)	r2, [r0]
+3:	T(ldrb)	r3, [r0, #1]
+#else
+2:	T(ldrb)	r2, [r0], #1
+3:	T(ldrb)	r3, [r0]
+#endif
 #ifndef __ARMEB__
 	orr	r2, r2, r3, lsl #8
 #else
@@ -48,7 +54,7 @@ ENTRY(__get_user_2)
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-4:	ldrt	r2, [r0]
+4:	T(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_4)
@@ -59,9 +65,9 @@ __get_user_bad:
 	mov	pc, lr
 ENDPROC(__get_user_bad)
 
-.section __ex_table, "a"
+.pushsection __ex_table, "a"
 	.long	1b, __get_user_bad
 	.long	2b, __get_user_bad
 	.long	3b, __get_user_bad
 	.long	4b, __get_user_bad
-.previous
+.popsection
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index d658561..ff4f71b 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -75,7 +75,10 @@ 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		)
 		subcs	r2, r2, #1
 		bcs	2f
 		subs	r2, r2, #2
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 67964bc..6dc0648 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -1,7 +1,7 @@
 /*
  * linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
  *
- * Author: Nicolas Pitre <nico@cam.org>
+ * Author: Nicolas Pitre <nico@fluxnic.net>
  *   - contributed to gcc-3.4 on Sep 30, 2003
  *   - adapted for the Linux kernel on Oct 2, 2003
  */
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index 99ea338..f83d449 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -43,7 +43,9 @@ ENTRY(__aeabi_llsr)
 	rsb	ip, r2, #32
 	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/memcpy.S b/arch/arm/lib/memcpy.S
index e0d0026..a9b9e22 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
@@ -30,7 +33,7 @@
 	.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
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 1254918..938fc14 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -74,25 +74,25 @@ ENTRY(memmove)
 		rsb	ip, ip, #32
 		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]!
+6:		W(nop)
+		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(nop)
+		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			)
 
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 864f3c1..c023fc1 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -28,35 +28,51 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__put_user_1)
-1:	strbt	r2, [r0]
+1:	T(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
+#ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
-2:	strbt	r2, [r0], #1
-3:	strbt	ip, [r0]
+2:	T(strb)	r2, [r0]
+3:	T(strb)	ip, [r0, #1]
 #else
-2:	strbt	ip, [r0], #1
-3:	strbt	r2, [r0]
+2:	T(strb)	ip, [r0]
+3:	T(strb)	r2, [r0, #1]
 #endif
+#else	/* !CONFIG_THUMB2_KERNEL */
+#ifndef __ARMEB__
+2:	T(strb)	r2, [r0], #1
+3:	T(strb)	ip, [r0]
+#else
+2:	T(strb)	ip, [r0], #1
+3:	T(strb)	r2, [r0]
+#endif
+#endif	/* CONFIG_THUMB2_KERNEL */
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
-4:	strt	r2, [r0]
+4:	T(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
-5:	strt	r2, [r0], #4
-6:	strt	r3, [r0]
+#ifdef CONFIG_THUMB2_KERNEL
+5:	T(str)	r2, [r0]
+6:	T(str)	r3, [r0, #4]
+#else
+5:	T(str)	r2, [r0], #4
+6:	T(str)	r3, [r0]
+#endif
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_8)
@@ -66,11 +82,11 @@ __put_user_bad:
 	mov	pc, lr
 ENDPROC(__put_user_bad)
 
-.section __ex_table, "a"
+.pushsection __ex_table, "a"
 	.long	1b, __put_user_bad
 	.long	2b, __put_user_bad
 	.long	3b, __put_user_bad
 	.long	4b, __put_user_bad
 	.long	5b, __put_user_bad
 	.long	6b, __put_user_bad
-.previous
+.popsection
diff --git a/arch/arm/lib/sha1.S b/arch/arm/lib/sha1.S
index a16fb20..eb0edb8 100644
--- a/arch/arm/lib/sha1.S
+++ b/arch/arm/lib/sha1.S
@@ -3,7 +3,7 @@
  *
  *  SHA transform optimized for ARM
  *
- *  Copyright:	(C) 2005 by Nicolas Pitre <nico@cam.org>
+ *  Copyright:	(C) 2005 by Nicolas Pitre <nico@fluxnic.net>
  *  Created:	September 17, 2005
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -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/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
index 330373c..f202d7b 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
@@ -33,11 +33,11 @@ USER(	ldrplbt	r3, [r1], #1)
 	mov	pc, lr
 ENDPROC(__strncpy_from_user)
 
-	.section .fixup,"ax"
+	.pushsection .fixup,"ax"
 	.align	0
 9001:	mov	r3, #0
 	strb	r3, [r0, #0]	@ null terminate
 	mov	r0, #-EFAULT
 	mov	pc, lr
-	.previous
+	.popsection
 
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
index 90bb9d0..0ecbb45 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
@@ -33,8 +33,8 @@ USER(	ldrbt	r3, [r0], #1)
 	mov	pc, lr
 ENDPROC(__strnlen_user)
 
-	.section .fixup,"ax"
+	.pushsection .fixup,"ax"
 	.align	0
 9001:	mov	r0, #0
 	mov	pc, lr
-	.previous
+	.popsection
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index ffdd274..d0ece2a 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -14,6 +14,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 		.text
 
@@ -31,11 +32,11 @@
 		rsb	ip, ip, #4
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		sub	r2, r2, ip
 		b	.Lc2u_dest_aligned
 
@@ -58,7 +59,7 @@ ENTRY(__copy_to_user)
 		addmi	ip, r2, #4
 		bmi	.Lc2u_0nowords
 		ldr	r3, [r1], #4
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -87,18 +88,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
 		ldrne	r3, [r1], #4
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_0fupi
 .Lc2u_0nowords:	teq	ip, #0
 		beq	.Lc2u_finished
 .Lc2u_nowords:	cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_not_enough:
@@ -119,7 +120,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #8
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #24
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -154,18 +155,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #8
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #24
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
 .Lc2u_1nowords:	mov	r3, r7, get_byte_1
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_2
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		movgt	r3, r7, get_byte_3
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_2fupi:	subs	r2, r2, #4
@@ -174,7 +175,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #16
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #16
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -209,18 +210,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #16
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #16
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
 .Lc2u_2nowords:	mov	r3, r7, get_byte_2
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_3
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_3fupi:	subs	r2, r2, #4
@@ -229,7 +230,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #24
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #8
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -264,25 +265,25 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #24
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #8
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
 .Lc2u_3nowords:	mov	r3, r7, get_byte_3
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 ENDPROC(__copy_to_user)
 
-		.section .fixup,"ax"
+		.pushsection .fixup,"ax"
 		.align	0
 9001:		ldmfd	sp!, {r0, r4 - r7, pc}
-		.previous
+		.popsection
 
 /* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n);
  * Purpose  : copy a block from user memory to kernel memory
@@ -294,11 +295,11 @@ ENDPROC(__copy_to_user)
 .Lcfu_dest_not_aligned:
 		rsb	ip, ip, #4
 		cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		sub	r2, r2, ip
 		b	.Lcfu_dest_aligned
@@ -321,7 +322,7 @@ ENTRY(__copy_from_user)
 .Lcfu_0fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_0nowords
-USER(		ldrt	r3, [r1], #4)
+USER(		T(ldr)	r3, [r1], #4)
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
@@ -350,18 +351,18 @@ USER(		ldrt	r3, [r1], #4)
 		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		ldrnet	r3, [r1], #4			@ Shouldnt fault
+		T(ldrne) r3, [r1], #4			@ Shouldnt fault
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_0fupi
 .Lcfu_0nowords:	teq	ip, #0
 		beq	.Lcfu_finished
 .Lcfu_nowords:	cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -374,7 +375,7 @@ USER(		ldrgtbt	r3, [r1], #1)			@ May fault
 
 .Lcfu_src_not_aligned:
 		bic	r1, r1, #3
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		cmp	ip, #2
 		bgt	.Lcfu_3fupi
 		beq	.Lcfu_2fupi
@@ -382,7 +383,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
 		mov	r3, r7, pull #8
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -417,7 +418,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #8
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -437,7 +438,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
 		mov	r3, r7, pull #16
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -473,7 +474,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #16
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -485,7 +486,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		strb	r3, [r0], #1
 		movge	r3, r7, get_byte_3
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #0)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #0)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -493,7 +494,7 @@ USER(		ldrgtbt	r3, [r1], #0)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
 		mov	r3, r7, pull #24
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -528,7 +529,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #24
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -538,14 +539,14 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		beq	.Lcfu_finished
 		cmp	ip, #2
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 ENDPROC(__copy_from_user)
 
-		.section .fixup,"ax"
+		.pushsection .fixup,"ax"
 		.align	0
 		/*
 		 * We took an exception.  r0 contains a pointer to
@@ -559,5 +560,5 @@ ENDPROC(__copy_from_user)
 		blne	__memzero
 		mov	r0, r4
 		ldmfd	sp!, {r4 - r7, pc}
-		.previous
+		.popsection
 
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 6b967ff..e2d2f2c 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/hardirq.h> /* for in_atomic() */
+#include <linux/gfp.h>
 #include <asm/current.h>
 #include <asm/page.h>