armv8: layerscape: rework spin table

There are two issues:

 (1) The spin table doesn't convert the endianness of the jump address.
     Although there is code for it, the result isn't used at all (x0).
 (2) If something goes wrong, the function returns. But that doesn't
     make sense at all.

Use the actual converted jump address as destination to fix. If
there is an error, jump to a trap loop. And rearrange the code exception
level switching code to make it smaller and clearer.

This reduces the size of the spin table code section from 696 bytes to
424 bytes. If CONFIG_ARMV8_SWITCH_TO_EL1 the code size reduced from 696
bytes to 632 bytes.
Signed-off-by: NMichael Walle <michael@walle.cc>
Reviewed-by: NPriyanka Jain <priyanka.jain@nxp.com>

arch/arm/cpu/armv8/fsl-layerscape/spintable.S

@@ -31,7 +31,7 @@ __spin_table:
 	.space CONFIG_MAX_CPUS*SPIN_TABLE_ELEM_SIZE
 
 	.align 2
-ENTRY(__secondary_boot_func)
+__secondary_boot_func:
 	/*
 	 * MPIDR_EL1 Fields:
 	 * MPIDR[1:0] = AFF0_CPUID <- Core ID (0,1)
@@ -72,73 +72,36 @@ ENTRY(__secondary_boot_func)
 	str	x4, [x11, #8]	/* STATUS */
 	dsb	sy
 
-slave_cpu:
+1:
 	wfe
-	ldr	x0, [x11]
-	cbz	x0, slave_cpu
-#ifndef CONFIG_ARMV8_SWITCH_TO_EL1
+	ldr	x4, [x11]
+	cbz	x4, 1b
 	mrs     x1, sctlr_el2
-#else
-	mrs     x1, sctlr_el1
-#endif
-	tbz     x1, #25, cpu_is_le
-	rev     x0, x0                  /* BE to LE conversion */
-cpu_is_le:
-	ldr	x5, [x11, #24]
-	cbz	x5, 1f
-
+	tbz     x1, #25, 2f
+	rev     x4, x4                  /* BE to LE conversion */
+2:
+	ldr	x6, =ES_TO_AARCH64
 #ifdef CONFIG_ARMV8_SWITCH_TO_EL1
-	adr	x4, secondary_switch_to_el1
-	ldr	x5, =ES_TO_AARCH64
-#else
-	ldr	x4, [x11]
-	ldr	x5, =ES_TO_AARCH32
+	adr	x5, 3f
+	switch_el x7, 0f, _dead_loop, _dead_loop
+0:	armv8_switch_to_el2_m x5, x6, x7
 #endif
-	bl	secondary_switch_to_el2
-
-1:
+3:
+	ldr	x7, [x11, #24]	/* ARCH_COMP */
+	cbz	x7, 4f
+	ldr	x6, =ES_TO_AARCH32
+4:
 #ifdef CONFIG_ARMV8_SWITCH_TO_EL1
-	adr	x4, secondary_switch_to_el1
+	switch_el x7, _dead_loop, 0f, _dead_loop
+0:	armv8_switch_to_el1_m x4, x6, x7
 #else
-	ldr	x4, [x11]
+	switch_el x7, 0f, _dead_loop, _dead_loop
+0:	armv8_switch_to_el2_m x4, x6, x7
 #endif
-	ldr	x5, =ES_TO_AARCH64
-	bl	secondary_switch_to_el2
-
-ENDPROC(__secondary_boot_func)
-
-ENTRY(secondary_switch_to_el2)
-	switch_el x6, 1f, 0f, 0f
-0:	ret
-1:	armv8_switch_to_el2_m x4, x5, x6
-ENDPROC(secondary_switch_to_el2)
-
-ENTRY(secondary_switch_to_el1)
-	mrs	x0, mpidr_el1
-	ubfm	x1, x0, #8, #15
-	ubfm	x2, x0, #0, #1
-	orr	x10, x2, x1, lsl #2	/* x10 has LPID */
-
-	lsl	x1, x10, #6
-	adr	x0, __spin_table
-	/* physical address of this cpus spin table element */
-	add	x11, x1, x0
-
-	ldr	x4, [x11]
-
-	ldr	x5, [x11, #24]
-	cbz	x5, 2f
 
-	ldr	x5, =ES_TO_AARCH32
-	bl	switch_to_el1
-
-2:	ldr	x5, =ES_TO_AARCH64
-
-switch_to_el1:
-	switch_el x6, 0f, 1f, 0f
-0:	ret
-1:	armv8_switch_to_el1_m x4, x5, x6
-ENDPROC(secondary_switch_to_el1)
+_dead_loop:
+	wfe
+	b _dead_loop
 
 	/* Ensure that the literals used by the secondary boot code are
 	 * assembled within it (this is required so that we can protect