Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Updates for IRQ stacks and virtually mapped stack support, and ftrace:

   - Support for IRQ and vmap'ed stacks

     This covers all the work related to implementing IRQ stacks and
     vmap'ed stacks for all 32-bit ARM systems that are currently
     supported by the Linux kernel, including RiscPC and Footbridge. It
     has been submitted for review in four different waves:

      - IRQ stacks support for v7 SMP systems [0]

      - vmap'ed stacks support for v7 SMP systems[1]

      - extending support for both IRQ stacks and vmap'ed stacks for all
        remaining configurations, including v6/v7 SMP multiplatform
        kernels and uniprocessor configurations including v7-M [2]

      - fixes and updates in [3]

   - ftrace fixes and cleanups

     Make all flavors of ftrace available on all builds, regardless of
     ISA choice, unwinder choice or compiler [4]:

      - use ADD not POP where possible

      - fix a couple of Thumb2 related issues

      - enable HAVE_FUNCTION_GRAPH_FP_TEST for robustness

      - enable the graph tracer with the EABI unwinder

      - avoid clobbering frame pointer registers to make Clang happy

   - Fixes for the above"

[0] https://lore.kernel.org/linux-arm-kernel/20211115084732.3704393-1-ardb@kernel.org/
[1] https://lore.kernel.org/linux-arm-kernel/20211122092816.2865873-1-ardb@kernel.org/
[2] https://lore.kernel.org/linux-arm-kernel/20211206164659.1495084-1-ardb@kernel.org/
[3] https://lore.kernel.org/linux-arm-kernel/20220124174744.1054712-1-ardb@kernel.org/
[4] https://lore.kernel.org/linux-arm-kernel/20220203082204.1176734-1-ardb@kernel.org/

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (62 commits)
  ARM: fix building NOMMU ARMv4/v5 kernels
  ARM: unwind: only permit stack switch when unwinding call_with_stack()
  ARM: Revert "unwind: dump exception stack from calling frame"
  ARM: entry: fix unwinder problems caused by IRQ stacks
  ARM: unwind: set frame.pc correctly for current-thread unwinding
  ARM: 9184/1: return_address: disable again for CONFIG_ARM_UNWIND=y
  ARM: 9183/1: unwind: avoid spurious warnings on bogus code addresses
  Revert "ARM: 9144/1: forbid ftrace with clang and thumb2_kernel"
  ARM: mach-bcm: disable ftrace in SMC invocation routines
  ARM: cacheflush: avoid clobbering the frame pointer
  ARM: kprobes: treat R7 as the frame pointer register in Thumb2 builds
  ARM: ftrace: enable the graph tracer with the EABI unwinder
  ARM: unwind: track location of LR value in stack frame
  ARM: ftrace: enable HAVE_FUNCTION_GRAPH_FP_TEST
  ARM: ftrace: avoid unnecessary literal loads
  ARM: ftrace: avoid redundant loads or clobbering IP
  ARM: ftrace: use trampolines to keep .init.text in branching range
  ARM: ftrace: use ADD not POP to counter PUSH at entry
  ARM: ftrace: ensure that ADR takes the Thumb bit into account
  ARM: make get_current() and __my_cpu_offset() __always_inline
  ...

9 files changed, 105 insertions, 123 deletions

diff --git a/arch/arm/lib/backtrace-clang.S b/arch/arm/lib/backtrace-clang.S
index 5b2cdb1003e3..290c52a60fc6 100644
--- a/arch/arm/lib/backtrace-clang.S
+++ b/arch/arm/lib/backtrace-clang.S
@@ -144,7 +144,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
  */
 1003:		ldr	sv_lr, [sv_fp, #4]	@ get saved lr from next frame
 
-		ldr	r0, [sv_lr, #-4]	@ get call instruction
+1004:		ldr	r0, [sv_lr, #-4]	@ get call instruction
 		ldr	r3, .Lopcode+4
 		and	r2, r3, r0		@ is this a bl call
 		teq	r2, r3
@@ -164,7 +164,7 @@ finished_setup:
 /*
  * Print the function (sv_pc) and where it was called from (sv_lr).
  */
-1004:		mov	r0, sv_pc
+		mov	r0, sv_pc
 
 		mov	r1, sv_lr
 		mov	r2, frame
@@ -197,6 +197,14 @@ finished_setup:
 
 		cmp	sv_fp, frame		@ next frame must be
 		mov	frame, sv_fp		@ above the current frame
+#ifdef CONFIG_IRQSTACKS
+		@
+		@ Kernel stacks may be discontiguous in memory. If the next
+		@ frame is below the previous frame, accept it as long as it
+		@ lives in kernel memory.
+		@
+		cmpls	sv_fp, #PAGE_OFFSET
+#endif
 		bhi	for_each_frame
 
 1006:		adr	r0, .Lbad
@@ -210,7 +218,7 @@ ENDPROC(c_backtrace)
 		.long	1001b, 1006b
 		.long	1002b, 1006b
 		.long	1003b, 1006b
-		.long	1004b, 1006b
+		.long	1004b, finished_setup
 		.long   1005b, 1006b
 		.popsection
 
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index e8408f22d4dc..293a2716bd20 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -98,6 +98,14 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 
 		cmp	sv_fp, frame		@ next frame must be
 		mov	frame, sv_fp		@ above the current frame
+#ifdef CONFIG_IRQSTACKS
+		@
+		@ Kernel stacks may be discontiguous in memory. If the next
+		@ frame is below the previous frame, accept it as long as it
+		@ lives in kernel memory.
+		@
+		cmpls	sv_fp, #PAGE_OFFSET
+#endif
 		bhi	for_each_frame
 
 1006:		adr	r0, .Lbad
diff --git a/arch/arm/lib/call_with_stack.S b/arch/arm/lib/call_with_stack.S
index 28b0341ae786..0a268a6c513c 100644
--- a/arch/arm/lib/call_with_stack.S
+++ b/arch/arm/lib/call_with_stack.S
@@ -8,25 +8,42 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/unwind.h>
 
 /*
  * void call_with_stack(void (*fn)(void *), void *arg, void *sp)
  *
  * Change the stack to that pointed at by sp, then invoke fn(arg) with
  * the new stack.
+ *
+ * The sequence below follows the APCS frame convention for frame pointer
+ * unwinding, and implements the unwinder annotations needed by the EABI
+ * unwinder.
  */
-ENTRY(call_with_stack)
-	str	sp, [r2, #-4]!
-	str	lr, [r2, #-4]!
 
+ENTRY(call_with_stack)
+#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC)
+	mov	ip, sp
+	push	{fp, ip, lr, pc}
+	sub	fp, ip, #4
+#else
+UNWIND( .fnstart		)
+UNWIND( .save	{fpreg, lr}	)
+	push	{fpreg, lr}
+UNWIND( .setfp	fpreg, sp	)
+	mov	fpreg, sp
+#endif
 	mov	sp, r2
 	mov	r2, r0
 	mov	r0, r1
 
-	badr	lr, 1f
-	ret	r2
+	bl_r	r2
 
-1:	ldr	lr, [sp]
-	ldr	sp, [sp, #4]
-	ret	lr
+#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC)
+	ldmdb	fp, {fp, sp, pc}
+#else
+	mov	sp, fpreg
+	pop	{fpreg, pc}
+UNWIND( .fnend			)
+#endif
 ENDPROC(call_with_stack)
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 480a20766137..270de7debd0f 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -91,18 +91,15 @@
 	strb\cond \reg, [\ptr], #1
 	.endm
 
-	.macro enter reg1 reg2
+	.macro enter regs:vararg
 	mov	r3, #0
-	stmdb	sp!, {r0, r2, r3, \reg1, \reg2}
+UNWIND( .save	{r0, r2, r3, \regs}		)
+	stmdb	sp!, {r0, r2, r3, \regs}
 	.endm
 
-	.macro usave reg1 reg2
-	UNWIND(	.save {r0, r2, r3, \reg1, \reg2}	)
-	.endm
-
-	.macro exit reg1 reg2
+	.macro exit regs:vararg
 	add	sp, sp, #8
-	ldmfd	sp!, {r0, \reg1, \reg2}
+	ldmfd	sp!, {r0, \regs}
 	.endm
 
 	.text
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 810a805d36dc..8fbafb074fe9 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -69,13 +69,10 @@
  *	than one 32bit instruction in Thumb-2)
  */
 
-
-	UNWIND(	.fnstart			)
-		enter	r4, lr
-	UNWIND(	.fnend				)
-
 	UNWIND(	.fnstart			)
-		usave	r4, lr			  @ in first stmdb block
+		enter	r4, UNWIND(fpreg,) lr
+	UNWIND(	.setfp	fpreg, sp		)
+	UNWIND(	mov	fpreg, sp		)
 
 		subs	r2, r2, #4
 		blt	8f
@@ -86,12 +83,7 @@
 		bne	10f
 
 1:		subs	r2, r2, #(28)
-		stmfd	sp!, {r5 - r8}
-	UNWIND(	.fnend				)
-
-	UNWIND(	.fnstart			)
-		usave	r4, lr
-	UNWIND(	.save	{r5 - r8}		) @ in second stmfd block
+		stmfd	sp!, {r5, r6, r8, r9}
 		blt	5f
 
 	CALGN(	ands	ip, r0, #31		)
@@ -110,9 +102,9 @@
 	PLD(	pld	[r1, #92]		)
 
 3:	PLD(	pld	[r1, #124]		)
-4:		ldr8w	r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+4:		ldr8w	r1, r3, r4, r5, r6, r8, r9, ip, lr, abort=20f
 		subs	r2, r2, #32
-		str8w	r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+		str8w	r0, r3, r4, r5, r6, r8, r9, ip, lr, abort=20f
 		bge	3b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	4b			)
@@ -132,8 +124,8 @@
 		ldr1w	r1, r4, abort=20f
 		ldr1w	r1, r5, abort=20f
 		ldr1w	r1, r6, abort=20f
-		ldr1w	r1, r7, abort=20f
 		ldr1w	r1, r8, abort=20f
+		ldr1w	r1, r9, abort=20f
 		ldr1w	r1, lr, abort=20f
 
 #if LDR1W_SHIFT < STR1W_SHIFT
@@ -150,17 +142,14 @@
 		str1w	r0, r4, abort=20f
 		str1w	r0, r5, abort=20f
 		str1w	r0, r6, abort=20f
-		str1w	r0, r7, abort=20f
 		str1w	r0, r8, abort=20f
+		str1w	r0, r9, abort=20f
 		str1w	r0, lr, abort=20f
 
 	CALGN(	bcs	2b			)
 
-7:		ldmfd	sp!, {r5 - r8}
-	UNWIND(	.fnend				) @ end of second stmfd block
+7:		ldmfd	sp!, {r5, r6, r8, r9}
 
-	UNWIND(	.fnstart			)
-		usave	r4, lr			  @ still in first stmdb block
 8:		movs	r2, r2, lsl #31
 		ldr1b	r1, r3, ne, abort=21f
 		ldr1b	r1, r4, cs, abort=21f
@@ -169,7 +158,7 @@
 		str1b	r0, r4, cs, abort=21f
 		str1b	r0, ip, cs, abort=21f
 
-		exit	r4, pc
+		exit	r4, UNWIND(fpreg,) pc
 
 9:		rsb	ip, ip, #4
 		cmp	ip, #2
@@ -189,13 +178,10 @@
 		ldr1w	r1, lr, abort=21f
 		beq	17f
 		bgt	18f
-	UNWIND(	.fnend				)
 
 
 		.macro	forward_copy_shift pull push
 
-	UNWIND(	.fnstart			)
-		usave	r4, lr			  @ still in first stmdb block
 		subs	r2, r2, #28
 		blt	14f
 
@@ -205,12 +191,8 @@
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
-11:		stmfd	sp!, {r5 - r9}
-	UNWIND(	.fnend				)
+11:		stmfd	sp!, {r5, r6, r8 - r10}
 
-	UNWIND(	.fnstart			)
-		usave	r4, lr
-	UNWIND(	.save	{r5 - r9}		) @ in new second stmfd block
 	PLD(	pld	[r1, #0]		)
 	PLD(	subs	r2, r2, #96		)
 	PLD(	pld	[r1, #28]		)
@@ -219,35 +201,32 @@
 	PLD(	pld	[r1, #92]		)
 
 12:	PLD(	pld	[r1, #124]		)
-13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
+13:		ldr4w	r1, r4, r5, r6, r8, abort=19f
 		mov	r3, lr, lspull #\pull
 		subs	r2, r2, #32
-		ldr4w	r1, r8, r9, ip, lr, abort=19f
+		ldr4w	r1, r9, r10, ip, lr, abort=19f
 		orr	r3, r3, r4, lspush #\push
 		mov	r4, r4, lspull #\pull
 		orr	r4, r4, r5, lspush #\push
 		mov	r5, r5, lspull #\pull
 		orr	r5, r5, r6, lspush #\push
 		mov	r6, r6, lspull #\pull
-		orr	r6, r6, r7, lspush #\push
-		mov	r7, r7, lspull #\pull
-		orr	r7, r7, r8, lspush #\push
+		orr	r6, r6, r8, lspush #\push
 		mov	r8, r8, lspull #\pull
 		orr	r8, r8, r9, lspush #\push
 		mov	r9, r9, lspull #\pull
-		orr	r9, r9, ip, lspush #\push
+		orr	r9, r9, r10, lspush #\push
+		mov	r10, r10, lspull #\pull
+		orr	r10, r10, ip, lspush #\push
 		mov	ip, ip, lspull #\pull
 		orr	ip, ip, lr, lspush #\push
-		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, abort=19f
+		str8w	r0, r3, r4, r5, r6, r8, r9, r10, ip, abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	13b			)
 
-		ldmfd	sp!, {r5 - r9}
-	UNWIND(	.fnend				) @ end of the second stmfd block
+		ldmfd	sp!, {r5, r6, r8 - r10}
 
-	UNWIND(	.fnstart			)
-		usave	r4, lr			  @ still in first stmdb block
 14:		ands	ip, r2, #28
 		beq	16f
 
@@ -262,7 +241,6 @@
 
 16:		sub	r1, r1, #(\push / 8)
 		b	8b
-	UNWIND(	.fnend				)
 
 		.endm
 
@@ -273,6 +251,7 @@
 
 18:		forward_copy_shift	pull=24	push=8
 
+	UNWIND(	.fnend				)
 
 /*
  * Abort preamble and completion macros.
@@ -282,13 +261,13 @@
  */
 
 	.macro	copy_abort_preamble
-19:	ldmfd	sp!, {r5 - r9}
+19:	ldmfd	sp!, {r5, r6, r8 - r10}
 	b	21f
-20:	ldmfd	sp!, {r5 - r8}
+20:	ldmfd	sp!, {r5, r6, r8, r9}
 21:
 	.endm
 
 	.macro	copy_abort_end
-	ldmfd	sp!, {r4, pc}
+	ldmfd	sp!, {r4, UNWIND(fpreg,) pc}
 	.endm
 
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 842ea5ede485..fac49e57cc0b 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -90,18 +90,15 @@
 	strusr	\reg, \ptr, 1, \cond, abort=\abort
 	.endm
 
-	.macro enter reg1 reg2
+	.macro enter regs:vararg
 	mov	r3, #0
-	stmdb	sp!, {r0, r2, r3, \reg1, \reg2}
+UNWIND( .save	{r0, r2, r3, \regs}		)
+	stmdb	sp!, {r0, r2, r3, \regs}
 	.endm
 
-	.macro usave reg1 reg2
-	UNWIND(	.save {r0, r2, r3, \reg1, \reg2}	)
-	.endm
-
-	.macro exit reg1 reg2
+	.macro exit regs:vararg
 	add	sp, sp, #8
-	ldmfd	sp!, {r0, \reg1, \reg2}
+	ldmfd	sp!, {r0, \regs}
 	.endm
 
 	.text
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index e4caf48c089f..90f2b645aa0d 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -42,16 +42,13 @@
 	strb\cond \reg, [\ptr], #1
 	.endm
 
-	.macro enter reg1 reg2
-	stmdb sp!, {r0, \reg1, \reg2}
+	.macro enter regs:vararg
+UNWIND( .save	{r0, \regs}		)
+	stmdb sp!, {r0, \regs}
 	.endm
 
-	.macro usave reg1 reg2
-	UNWIND(	.save	{r0, \reg1, \reg2}	)
-	.endm
-
-	.macro exit reg1 reg2
-	ldmfd sp!, {r0, \reg1, \reg2}
+	.macro exit regs:vararg
+	ldmfd sp!, {r0, \regs}
 	.endm
 
 	.text
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 6fecc12a1f51..6410554039fd 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -31,12 +31,13 @@ WEAK(memmove)
 		subs	ip, r0, r1
 		cmphi	r2, ip
 		bls	__memcpy
-
-		stmfd	sp!, {r0, r4, lr}
 	UNWIND(	.fnend				)
 
 	UNWIND(	.fnstart			)
-	UNWIND(	.save	{r0, r4, lr}		) @ in first stmfd block
+	UNWIND(	.save	{r0, r4, fpreg, lr}	)
+		stmfd	sp!, {r0, r4, UNWIND(fpreg,) lr}
+	UNWIND(	.setfp	fpreg, sp		)
+	UNWIND(	mov	fpreg, sp		)
 		add	r1, r1, r2
 		add	r0, r0, r2
 		subs	r2, r2, #4
@@ -48,12 +49,7 @@ WEAK(memmove)
 		bne	10f
 
 1:		subs	r2, r2, #(28)
-		stmfd	sp!, {r5 - r8}
-	UNWIND(	.fnend				)
-
-	UNWIND(	.fnstart			)
-	UNWIND(	.save	{r0, r4, lr}		)
-	UNWIND(	.save	{r5 - r8}		) @ in second stmfd block
+		stmfd	sp!, {r5, r6, r8, r9}
 		blt	5f
 
 	CALGN(	ands	ip, r0, #31		)
@@ -72,9 +68,9 @@ WEAK(memmove)
 	PLD(	pld	[r1, #-96]		)
 
 3:	PLD(	pld	[r1, #-128]		)
-4:		ldmdb	r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
+4:		ldmdb	r1!, {r3, r4, r5, r6, r8, r9, ip, lr}
 		subs	r2, r2, #32
-		stmdb	r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
+		stmdb	r0!, {r3, r4, r5, r6, r8, r9, ip, lr}
 		bge	3b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	4b			)
@@ -88,8 +84,8 @@ WEAK(memmove)
 		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)	r9, [r1, #-4]!
 		W(ldr)	lr, [r1, #-4]!
 
 		add	pc, pc, ip
@@ -99,17 +95,13 @@ WEAK(memmove)
 		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)	r9, [r0, #-4]!
 		W(str)	lr, [r0, #-4]!
 
 	CALGN(	bcs	2b			)
 
-7:		ldmfd	sp!, {r5 - r8}
-	UNWIND(	.fnend				) @ end of second stmfd block
-
-	UNWIND(	.fnstart			)
-	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block
+7:		ldmfd	sp!, {r5, r6, r8, r9}
 
 8:		movs	r2, r2, lsl #31
 		ldrbne	r3, [r1, #-1]!
@@ -118,7 +110,7 @@ WEAK(memmove)
 		strbne	r3, [r0, #-1]!
 		strbcs	r4, [r0, #-1]!
 		strbcs	ip, [r0, #-1]
-		ldmfd	sp!, {r0, r4, pc}
+		ldmfd	sp!, {r0, r4, UNWIND(fpreg,) pc}
 
 9:		cmp	ip, #2
 		ldrbgt	r3, [r1, #-1]!
@@ -137,13 +129,10 @@ WEAK(memmove)
 		ldr	r3, [r1, #0]
 		beq	17f
 		blt	18f
-	UNWIND(	.fnend				)
 
 
 		.macro	backward_copy_shift push pull
 
-	UNWIND(	.fnstart			)
-	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block
 		subs	r2, r2, #28
 		blt	14f
 
@@ -152,12 +141,7 @@ WEAK(memmove)
 	CALGN(	subcc	r2, r2, ip		)
 	CALGN(	bcc	15f			)
 
-11:		stmfd	sp!, {r5 - r9}
-	UNWIND(	.fnend				)
-
-	UNWIND(	.fnstart			)
-	UNWIND(	.save	{r0, r4, lr}		)
-	UNWIND(	.save	{r5 - r9}		) @ in new second stmfd block
+11:		stmfd	sp!, {r5, r6, r8 - r10}
 
 	PLD(	pld	[r1, #-4]		)
 	PLD(	subs	r2, r2, #96		)
@@ -167,35 +151,31 @@ WEAK(memmove)
 	PLD(	pld	[r1, #-96]		)
 
 12:	PLD(	pld	[r1, #-128]		)
-13:		ldmdb   r1!, {r7, r8, r9, ip}
+13:		ldmdb   r1!, {r8, r9, r10, ip}
 		mov     lr, r3, lspush #\push
 		subs    r2, r2, #32
 		ldmdb   r1!, {r3, r4, r5, r6}
 		orr     lr, lr, ip, lspull #\pull
 		mov     ip, ip, lspush #\push
-		orr     ip, ip, r9, lspull #\pull
+		orr     ip, ip, r10, lspull #\pull
+		mov     r10, r10, lspush #\push
+		orr     r10, r10, r9, lspull #\pull
 		mov     r9, r9, lspush #\push
 		orr     r9, r9, r8, lspull #\pull
 		mov     r8, r8, lspush #\push
-		orr     r8, r8, r7, lspull #\pull
-		mov     r7, r7, lspush #\push
-		orr     r7, r7, r6, lspull #\pull
+		orr     r8, r8, r6, lspull #\pull
 		mov     r6, r6, lspush #\push
 		orr     r6, r6, r5, lspull #\pull
 		mov     r5, r5, lspush #\push
 		orr     r5, r5, r4, lspull #\pull
 		mov     r4, r4, lspush #\push
 		orr     r4, r4, r3, lspull #\pull
-		stmdb   r0!, {r4 - r9, ip, lr}
+		stmdb   r0!, {r4 - r6, r8 - r10, ip, lr}
 		bge	12b
 	PLD(	cmn	r2, #96			)
 	PLD(	bge	13b			)
 
-		ldmfd	sp!, {r5 - r9}
-	UNWIND(	.fnend				) @ end of the second stmfd block
-
-	UNWIND(	.fnstart			)
-	UNWIND(	.save {r0, r4, lr}		) @ still in first stmfd block
+		ldmfd	sp!, {r5, r6, r8 - r10}
 
 14:		ands	ip, r2, #28
 		beq	16f
@@ -211,7 +191,6 @@ WEAK(memmove)
 
 16:		add	r1, r1, #(\pull / 8)
 		b	8b
-	UNWIND(	.fnend				)
 
 		.endm
 
@@ -222,5 +201,6 @@ WEAK(memmove)
 
 18:		backward_copy_shift	push=24	pull=8
 
+	UNWIND(	.fnend				)
 ENDPROC(memmove)
 ENDPROC(__memmove)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 9817cb258c1a..d71ab61430b2 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -28,16 +28,16 @@ UNWIND( .fnstart         )
 	mov	r3, r1
 7:	cmp	r2, #16
 	blt	4f
+UNWIND( .fnend              )
 
 #if ! CALGN(1)+0
 
 /*
  * We need 2 extra registers for this loop - use r8 and the LR
  */
-	stmfd	sp!, {r8, lr}
-UNWIND( .fnend              )
 UNWIND( .fnstart            )
 UNWIND( .save {r8, lr}      )
+	stmfd	sp!, {r8, lr}
 	mov	r8, r1
 	mov	lr, r3
 
@@ -66,10 +66,9 @@ UNWIND( .fnend              )
  * whole cache lines at once.
  */
 
-	stmfd	sp!, {r4-r8, lr}
-UNWIND( .fnend                 )
 UNWIND( .fnstart               )
 UNWIND( .save {r4-r8, lr}      )
+	stmfd	sp!, {r4-r8, lr}
 	mov	r4, r1
 	mov	r5, r3
 	mov	r6, r1