diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 633d1cb84d87..9e92cb205e65 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -81,6 +81,10 @@ extern void cpu_dcache_clean_area(void *, int);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+
+/* These three are private to arch/arm/kernel/suspend.c */
+extern void cpu_do_suspend(void *);
+extern void cpu_do_resume(void *);
 #else
 #define cpu_proc_init			processor._proc_init
 #define cpu_proc_fin			processor._proc_fin
@@ -89,6 +93,10 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #define cpu_dcache_clean_area		processor.dcache_clean_area
 #define cpu_set_pte_ext			processor.set_pte_ext
 #define cpu_do_switch_mm		processor.switch_mm
+
+/* These three are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			processor.do_suspend
+#define cpu_do_resume			processor.do_resume
 #endif
 
 extern void cpu_resume(void);
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index c9a43caaea80..020e99c845e7 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -8,54 +8,35 @@
 	.text
 
 /*
- * Save CPU state for a suspend
- *  r0 = phys addr of temporary page tables
- *  r1 = v:p offset
- *  r2 = suspend function arg0
- *  r3 = suspend function
+ * Save CPU state for a suspend.  This saves the CPU general purpose
+ * registers, and allocates space on the kernel stack to save the CPU
+ * specific registers and some other data for resume.
+ *  r0 = suspend function arg0
+ *  r1 = suspend function
  */
 ENTRY(__cpu_suspend)
 	stmfd	sp!, {r4 - r11, lr}
-	mov	r4, r0
 #ifdef MULTI_CPU
 	ldr	r10, =processor
-	ldr	r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
-	ldr	ip, [r10, #CPU_DO_RESUME] @ virtual resume function
+	ldr	r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state
 #else
-	ldr	r5, =cpu_suspend_size
-	ldr	ip, =cpu_do_resume
+	ldr	r4, =cpu_suspend_size
 #endif
-	mov	r6, sp			@ current virtual SP
-	sub	sp, sp, r5		@ allocate CPU state on stack
-	mov	r0, sp			@ save pointer to CPU save block
-	add	ip, ip, r1		@ convert resume fn to phys
-	stmfd	sp!, {r4, r6, ip}	@ save phys pgd, virt SP, phys resume fn
-	ldr	r5, =sleep_save_sp
-	add	r6, sp, r1		@ convert SP to phys
-	stmfd	sp!, {r2, r3}		@ save suspend func arg and pointer
+	mov	r5, sp			@ current virtual SP
+	add	r4, r4, #12		@ Space for pgd, virt sp, phys resume fn
+	sub	sp, sp, r4		@ allocate CPU state on stack
+	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
+	add	r0, sp, #8		@ save pointer to save block
+	mov	r1, r4			@ size of save block
+	mov	r2, r5			@ virtual SP
+	ldr	r3, =sleep_save_sp
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
 	ALT_UP(mov lr, #0)
 	and	lr, lr, #15
-	str	r6, [r5, lr, lsl #2]	@ save phys SP
-#else
-	str	r6, [r5]		@ save phys SP
-#endif
-#ifdef MULTI_CPU
-	mov	lr, pc
-	ldr	pc, [r10, #CPU_DO_SUSPEND] @ save CPU state
-#else
-	bl	cpu_do_suspend
-#endif
-
-	@ flush data cache
-#ifdef MULTI_CACHE
-	ldr	r10, =cpu_cache
-	mov	lr, pc
-	ldr	pc, [r10, #CACHE_FLUSH_KERN_ALL]
-#else
-	bl	__cpuc_flush_kern_all
+	add	r3, r3, lr, lsl #2
 #endif
+	bl	__cpu_suspend_save
 	adr	lr, BSYM(cpu_suspend_abort)
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
 ENDPROC(__cpu_suspend)
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index ed4160b64e66..2d60f1903206 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -8,9 +8,28 @@
 
 static pgd_t *suspend_pgd;
 
-extern int __cpu_suspend(int, long, unsigned long, int (*)(unsigned long));
+extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
 extern void cpu_resume_mmu(void);
 
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ */
+void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
+{
+	*save_ptr = virt_to_phys(ptr);
+
+	/* This must correspond to the LDM in cpu_resume() assembly */
+	*ptr++ = virt_to_phys(suspend_pgd);
+	*ptr++ = sp;
+	*ptr++ = virt_to_phys(cpu_do_resume);
+
+	cpu_do_suspend(ptr);
+
+	flush_cache_all();
+}
+
 /*
  * Hide the first two arguments to __cpu_suspend - these are an implementation
  * detail which platform code shouldn't have to know about.
@@ -29,8 +48,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * resume (indicated by a zero return code), we need to switch
 	 * back to the correct page tables.
 	 */
-	ret = __cpu_suspend(virt_to_phys(suspend_pgd),
-			    PHYS_OFFSET - PAGE_OFFSET, arg, fn);
+	ret = __cpu_suspend(arg, fn);
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_tlb_all();