ARM: Put target PC for PSCI CPU_ON on per-CPU stack

Use a per-CPU variable for saving the target PC during CPU_ON
operations. This allows us to run this service independently on targets
that have more than 2 cores and also core-local power control.

CC: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Tom Rini <trini@konsulko.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Tested-by: Thierry Reding <treding@nvidia.com>
Tested-by: Ian Campbell <ijc@hellion.org.uk>
Signed-off-by: Tom Warren <twarren@nvidia.com>
diff --git a/arch/arm/cpu/armv7/sunxi/psci.S b/arch/arm/cpu/armv7/sunxi/psci.S
index dd583b2..7ec0500 100644
--- a/arch/arm/cpu/armv7/sunxi/psci.S
+++ b/arch/arm/cpu/armv7/sunxi/psci.S
@@ -139,8 +139,11 @@
 	@ r2 = target PC
 .globl	psci_cpu_on
 psci_cpu_on:
-	ldr	r0, =_psci_target_pc
-	str	r2, [r0]
+	push	{lr}
+
+	mov	r0, r1
+	bl	psci_get_cpu_stack_top	@ get stack top of target CPU
+	str	r2, [r0]		@ store target PC at stack top
 	dsb
 
 	movw	r0, #(SUN7I_CPUCFG_BASE & 0xffff)
@@ -195,7 +198,7 @@
 	str	r6, [r0, #0x1e4]
 
 	mov	r0, #ARM_PSCI_RET_SUCCESS	@ Return PSCI_RET_SUCCESS
-	mov	pc, lr
+	pop	{pc}
 
 .globl	psci_cpu_off
 psci_cpu_off: