arm64: entry: Free up another register on kpti's tramp_exit path

Kpti stashes x30 in far_el1 while it uses x30 for all its work.

Making the vectors a per-cpu data structure will require a second
register.

Allow tramp_exit two registers before it unmaps the kernel, by
leaving x30 on the stack, and stashing x29 in far_el1.
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>

arch/arm64/kernel/entry.S

@@ -419,14 +419,16 @@ alternative_else_nop_endif
 	ldp	x24, x25, [sp, #16 * 12]
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
-alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+	eret
+alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	bne	4f
-	msr	far_el1, x30
+	msr	far_el1, x29
 	tramp_alias	x30, tramp_exit_native
 	br	x30
 4:
@@ -434,6 +436,9 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 	br	x30
 #endif
 	.else
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
 
@@ -674,10 +679,12 @@ alternative_else_nop_endif
 	.macro tramp_exit, regsize = 64
 	adr	x30, tramp_vectors
 	msr	vbar_el1, x30
-	tramp_unmap_kernel	x30
+	ldr	lr, [sp, #S_LR]
+	tramp_unmap_kernel	x29
 	.if	\regsize == 64
-	mrs	x30, far_el1
+	mrs	x29, far_el1
 	.endif
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 	eret
 	sb
 	.endm