diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 2f841cb65c30..a711322d9f40 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -150,21 +150,6 @@ extern unsigned long vectors_base;
  */
 #define PLAT_PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
 
-#ifdef CONFIG_XIP_KERNEL
-/*
- * When referencing data in RAM from the XIP region in a relative manner
- * with the MMU off, we need the relative offset between the two physical
- * addresses.  The macro below achieves this, which is:
- *    __pa(v_data) - __xip_pa(v_text)
- */
-#define PHYS_RELATIVE(v_data, v_text) \
-	(((v_data) - PAGE_OFFSET + PLAT_PHYS_OFFSET) - \
-	 ((v_text) - XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR) + \
-          CONFIG_XIP_PHYS_ADDR))
-#else
-#define PHYS_RELATIVE(v_data, v_text) ((v_data) - (v_text))
-#endif
-
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 76201ee9ee59..830bbfb26ca5 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -53,12 +53,12 @@ ENTRY(v7_invalidate_l1)
 	and	r2, r0, #0x7
 	add	r2, r2, #4		@ SetShift
 
-1:	movw	r4, #0x7fff
-	and	r0, r4, r0, lsr #13	@ 'NumSets' in CCSIDR[27:13]
+1:	movw	ip, #0x7fff
+	and	r0, ip, r0, lsr #13	@ 'NumSets' in CCSIDR[27:13]
 
-2:	mov	r4, r0, lsl r2		@ NumSet << SetShift
-	orr	r4, r4, r3		@ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
-	mcr	p15, 0, r4, c7, c6, 2
+2:	mov	ip, r0, lsl r2		@ NumSet << SetShift
+	orr	ip, ip, r3		@ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+	mcr	p15, 0, ip, c7, c6, 2
 	subs	r0, r0, #1		@ Set--
 	bpl	2b
 	subs	r3, r3, r1		@ Way--
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 28c9d32fa99a..26d726a08a34 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -256,6 +256,20 @@ ENDPROC(cpu_pj4b_do_resume)
 
 #endif
 
+	@
+	@ Invoke the v7_invalidate_l1() function, which adheres to the AAPCS
+	@ rules, and so it may corrupt registers that we need to preserve.
+	@
+	.macro	do_invalidate_l1
+	mov	r6, r1
+	mov	r7, r2
+	mov	r10, lr
+	bl	v7_invalidate_l1		@ corrupts {r0-r3, ip, lr}
+	mov	r1, r6
+	mov	r2, r7
+	mov	lr, r10
+	.endm
+
 /*
  *	__v7_setup
  *
@@ -277,6 +291,7 @@ __v7_ca5mp_setup:
 __v7_ca9mp_setup:
 __v7_cr7mp_setup:
 __v7_cr8mp_setup:
+	do_invalidate_l1
 	mov	r10, #(1 << 0)			@ Cache/TLB ops broadcasting
 	b	1f
 __v7_ca7mp_setup:
@@ -284,13 +299,9 @@ __v7_ca12mp_setup:
 __v7_ca15mp_setup:
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
+	do_invalidate_l1
 	mov	r10, #0
-1:	adr	r0, __v7_setup_stack_ptr
-	ldr	r12, [r0]
-	add	r12, r12, r0			@ the local stack
-	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
-	bl      v7_invalidate_l1
-	ldmia	r12, {r1-r6, lr}
+1:
 #ifdef CONFIG_SMP
 	orr	r10, r10, #(1 << 6)		@ Enable SMP/nAMP mode
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
@@ -471,12 +482,7 @@ __v7_pj4b_setup:
 #endif /* CONFIG_CPU_PJ4B */
 
 __v7_setup:
-	adr	r0, __v7_setup_stack_ptr
-	ldr	r12, [r0]
-	add	r12, r12, r0			@ the local stack
-	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
-	bl      v7_invalidate_l1
-	ldmia	r12, {r1-r6, lr}
+	do_invalidate_l1
 
 __v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
@@ -548,17 +554,8 @@ __errata_finish:
 	orr	r0, r0, r6			@ set them
  THUMB(	orr	r0, r0, #1 << 30	)	@ Thumb exceptions
 	ret	lr				@ return to head.S:__ret
-
-	.align	2
-__v7_setup_stack_ptr:
-	.word	PHYS_RELATIVE(__v7_setup_stack, .)
 ENDPROC(__v7_setup)
 
-	.bss
-	.align	2
-__v7_setup_stack:
-	.space	4 * 7				@ 7 registers
-
 	__INITDATA
 
 	.weak cpu_v7_bugs_init