arm64: switch_to: calculate cpu context pointer using separate register

Commit 0c8c0f03 ("x86/fpu, sched: Dynamically allocate 'struct fpu'")
moved the thread_struct to the bottom of task_struct. As a result, the
offset is now too large to be used in an immediate add on arm64 with
some kernel configs:

arch/arm64/kernel/entry.S: Assembler messages:
arch/arm64/kernel/entry.S:588: Error: immediate out of range
arch/arm64/kernel/entry.S:597: Error: immediate out of range

This patch calculates the offset using an additional register instead of
an immediate offset.

Fixes: 0c8c0f03 ("x86/fpu, sched: Dynamically allocate 'struct fpu'")
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/entry.S

@@ -585,7 +585,8 @@ ENDPROC(el0_irq)
  *
  */
 ENTRY(cpu_switch_to)
-	add	x8, x0, #THREAD_CPU_CONTEXT
+	mov	x10, #THREAD_CPU_CONTEXT
+	add	x8, x0, x10
 	mov	x9, sp
 	stp	x19, x20, [x8], #16		// store callee-saved registers
 	stp	x21, x22, [x8], #16
@@ -594,7 +595,7 @@ ENTRY(cpu_switch_to)
 	stp	x27, x28, [x8], #16
 	stp	x29, x9, [x8], #16
 	str	lr, [x8]
-	add	x8, x1, #THREAD_CPU_CONTEXT
+	add	x8, x1, x10
 	ldp	x19, x20, [x8], #16		// restore callee-saved registers
 	ldp	x21, x22, [x8], #16
 	ldp	x23, x24, [x8], #16