armv8: Support loading 32-bit OS in AArch32 execution state

To support loading a 32-bit OS, the execution state will change from
AArch64 to AArch32 when jumping to kernel.

The architecture information will be got through checking FIT image,
then U-Boot will load 32-bit OS or 64-bit OS automatically.

Signed-off-by: Ebony Zhu <ebony.zhu@nxp.com>
Signed-off-by: Alison Wang <alison.wang@nxp.com>
Signed-off-by: Chenhui Zhao <chenhui.zhao@nxp.com>
Reviewed-by: York Sun <york.sun@nxp.com>
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
index f7b49cb..72f2c11 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
+++ b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
@@ -17,6 +17,7 @@
 #include <asm/arch-fsl-layerscape/immap_lsch3.h>
 #include <asm/arch-fsl-layerscape/soc.h>
 #endif
+#include <asm/u-boot.h>
 
 ENTRY(lowlevel_init)
 	mov	x29, lr			/* Save LR */
@@ -359,11 +360,6 @@
         gic_wait_for_interrupt_m x0, w1
 #endif
 
-	bl secondary_switch_to_el2
-#ifdef CONFIG_ARMV8_SWITCH_TO_EL1
-	bl secondary_switch_to_el1
-#endif
-
 slave_cpu:
 	wfe
 	ldr	x0, [x11]
@@ -376,19 +372,64 @@
 	tbz     x1, #25, cpu_is_le
 	rev     x0, x0                  /* BE to LE conversion */
 cpu_is_le:
-	br	x0			/* branch to the given address */
+	ldr	x5, [x11, #24]
+	ldr	x6, =IH_ARCH_DEFAULT
+	cmp	x6, x5
+	b.eq	1f
+
+#ifdef CONFIG_ARMV8_SWITCH_TO_EL1
+	adr	x3, secondary_switch_to_el1
+	ldr	x4, =ES_TO_AARCH64
+#else
+	ldr	x3, [x11]
+	ldr	x4, =ES_TO_AARCH32
+#endif
+	bl	secondary_switch_to_el2
+
+1:
+#ifdef CONFIG_ARMV8_SWITCH_TO_EL1
+	adr	x3, secondary_switch_to_el1
+#else
+	ldr	x3, [x11]
+#endif
+	ldr	x4, =ES_TO_AARCH64
+	bl	secondary_switch_to_el2
+
 ENDPROC(secondary_boot_func)
 
 ENTRY(secondary_switch_to_el2)
-	switch_el x0, 1f, 0f, 0f
+	switch_el x5, 1f, 0f, 0f
 0:	ret
-1:	armv8_switch_to_el2_m x0
+1:	armv8_switch_to_el2_m x3, x4, x5
 ENDPROC(secondary_switch_to_el2)
 
 ENTRY(secondary_switch_to_el1)
-	switch_el x0, 0f, 1f, 0f
+	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
+	ldr	x0, =__spin_table
+	/* physical address of this cpus spin table element */
+	add	x11, x1, x0
+
+	ldr	x3, [x11]
+
+	ldr	x5, [x11, #24]
+	ldr	x6, =IH_ARCH_DEFAULT
+	cmp	x6, x5
+	b.eq	2f
+
+	ldr	x4, =ES_TO_AARCH32
+	bl	switch_to_el1
+
+2:	ldr	x4, =ES_TO_AARCH64
+
+switch_to_el1:
+	switch_el x5, 0f, 1f, 0f
 0:	ret
-1:	armv8_switch_to_el1_m x0, x1
+1:	armv8_switch_to_el1_m x3, x4, x5
 ENDPROC(secondary_switch_to_el1)
 
 	/* Ensure that the literals used by the secondary boot code are
diff --git a/arch/arm/cpu/armv8/start.S b/arch/arm/cpu/armv8/start.S
index 19c771d..4f5f6d8 100644
--- a/arch/arm/cpu/armv8/start.S
+++ b/arch/arm/cpu/armv8/start.S
@@ -251,9 +251,17 @@
 	/*
 	 * All slaves will enter EL2 and optionally EL1.
 	 */
+	adr	x3, lowlevel_in_el2
+	ldr	x4, =ES_TO_AARCH64
 	bl	armv8_switch_to_el2
+
+lowlevel_in_el2:
 #ifdef CONFIG_ARMV8_SWITCH_TO_EL1
+	adr	x3, lowlevel_in_el1
+	ldr	x4, =ES_TO_AARCH64
 	bl	armv8_switch_to_el1
+
+lowlevel_in_el1:
 #endif
 
 #endif /* CONFIG_ARMV8_MULTIENTRY */
diff --git a/arch/arm/cpu/armv8/transition.S b/arch/arm/cpu/armv8/transition.S
index 253a39b..bbccf2b 100644
--- a/arch/arm/cpu/armv8/transition.S
+++ b/arch/arm/cpu/armv8/transition.S
@@ -11,13 +11,24 @@
 #include <asm/macro.h>
 
 ENTRY(armv8_switch_to_el2)
-	switch_el x0, 1f, 0f, 0f
-0:	ret
-1:	armv8_switch_to_el2_m x0
+	switch_el x5, 1f, 0f, 0f
+0:
+	/*
+	 * x3 is kernel entry point or switch_to_el1
+	 * if CONFIG_ARMV8_SWITCH_TO_EL1 is defined.
+         * When running in EL2 now, jump to the
+	 * address saved in x3.
+	 */
+	br x3
+1:	armv8_switch_to_el2_m x3, x4, x5
 ENDPROC(armv8_switch_to_el2)
 
 ENTRY(armv8_switch_to_el1)
-	switch_el x0, 0f, 1f, 0f
-0:	ret
-1:	armv8_switch_to_el1_m x0, x1
+	switch_el x5, 0f, 1f, 0f
+0:
+	/* x3 is kernel entry point. When running in EL1
+	 * now, jump to the address saved in x3.
+	 */
+	br x3
+1:	armv8_switch_to_el1_m x3, x4, x5
 ENDPROC(armv8_switch_to_el1)