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/psci.S b/arch/arm/cpu/armv7/psci.S
index 18d85c4..87c0c0b 100644
--- a/arch/arm/cpu/armv7/psci.S
+++ b/arch/arm/cpu/armv7/psci.S
@@ -17,6 +17,7 @@
 
 #include <config.h>
 #include <linux/linkage.h>
+#include <asm/macro.h>
 #include <asm/psci.h>
 
 	.pushsection ._secure.text, "ax"
@@ -202,6 +203,7 @@
 	add	r5, r5, #0x2000			@ Skip two pages
 	lsr	r5, r5, #12			@ Align to start of page
 	lsl	r5, r5, #12
+	sub	r5, r5, #4			@ reserve 1 word for target PC
 	sub	r0, r5, r0			@ here's our stack!
 
 	bx	lr
@@ -212,13 +214,10 @@
 
 	bl	_nonsec_init
 
-	adr	r0, _psci_target_pc
-	ldr	r0, [r0]
+	bl	psci_get_cpu_id			@ CPU ID => r0
+	bl	psci_get_cpu_stack_top		@ stack top => r0
+	ldr	r0, [r0]			@ target PC at stack top
 	b	_do_nonsec_entry
 ENDPROC(psci_cpu_entry)
 
-.globl _psci_target_pc
-_psci_target_pc:
-	.word	0
-
 	.popsection