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/include/asm/arch-fsl-layerscape/mp.h b/arch/arm/include/asm/arch-fsl-layerscape/mp.h
index f7306ff..ebf84b6 100644
--- a/arch/arm/include/asm/arch-fsl-layerscape/mp.h
+++ b/arch/arm/include/asm/arch-fsl-layerscape/mp.h
@@ -36,4 +36,8 @@
 int is_core_online(u64 cpu_id);
 u32 cpu_pos_mask(void);
 #endif
+
+#define IH_ARCH_ARM		2	/* ARM */
+#define IH_ARCH_ARM64		22	/* ARM64 */
+
 #endif /* _FSL_LAYERSCAPE_MP_H */
diff --git a/arch/arm/include/asm/macro.h b/arch/arm/include/asm/macro.h
index 9bb0efa..2553e3e 100644
--- a/arch/arm/include/asm/macro.h
+++ b/arch/arm/include/asm/macro.h
@@ -8,6 +8,11 @@
 
 #ifndef __ASM_ARM_MACRO_H__
 #define __ASM_ARM_MACRO_H__
+
+#ifdef CONFIG_ARM64
+#include <asm/system.h>
+#endif
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -135,13 +140,21 @@
 #endif
 .endm
 
-.macro armv8_switch_to_el2_m, xreg1
-	/* 64bit EL2 | HCE | SMD | RES1 (Bits[5:4]) | Non-secure EL0/EL1 */
-	mov	\xreg1, #0x5b1
-	msr	scr_el3, \xreg1
+/*
+ * Switch from EL3 to EL2 for ARMv8
+ * @ep:     kernel entry point
+ * @flag:   The execution state flag for lower exception
+ *          level, ES_TO_AARCH64 or ES_TO_AARCH32
+ * @tmp:    temporary register
+ *
+ * For loading 32-bit OS, x1 is machine nr and x2 is ftaddr.
+ * For loading 64-bit OS, x0 is physical address to the FDT blob.
+ * They will be passed to the guest.
+ */
+.macro armv8_switch_to_el2_m, ep, flag, tmp
 	msr	cptr_el3, xzr		/* Disable coprocessor traps to EL3 */
-	mov	\xreg1, #0x33ff
-	msr	cptr_el2, \xreg1	/* Disable coprocessor traps to EL2 */
+	mov	\tmp, #CPTR_EL2_RES1
+	msr	cptr_el2, \tmp		/* Disable coprocessor traps to EL2 */
 
 	/* Initialize Generic Timers */
 	msr	cntvoff_el2, xzr
@@ -152,45 +165,90 @@
 	 * and RES0 bits (31,30,27,26,24,21,20,17,15-13,10-6) +
 	 * EE,WXN,I,SA,C,A,M to 0
 	 */
+	ldr	\tmp, =(SCTLR_EL2_RES1 | SCTLR_EL2_EE_LE |\
+			SCTLR_EL2_WXN_DIS | SCTLR_EL2_ICACHE_DIS |\
+			SCTLR_EL2_SA_DIS | SCTLR_EL2_DCACHE_DIS |\
+			SCTLR_EL2_ALIGN_DIS | SCTLR_EL2_MMU_DIS)
+	msr	sctlr_el2, \tmp
+
+	mov	\tmp, sp
+	msr	sp_el2, \tmp		/* Migrate SP */
+	mrs	\tmp, vbar_el3
+	msr	vbar_el2, \tmp		/* Migrate VBAR */
+
+	/* Check switch to AArch64 EL2 or AArch32 Hypervisor mode */
+	cmp	\flag, #ES_TO_AARCH32
+	b.eq	1f
+
+	/*
+	 * The next lower exception level is AArch64, 64bit EL2 | HCE |
+	 * SMD | RES1 (Bits[5:4]) | Non-secure EL0/EL1.
+	 */
-	mov	\xreg1, #0x0830
-	movk	\xreg1, #0x30C5, lsl #16
-	msr	sctlr_el2, \xreg1
+	ldr	\tmp, =(SCR_EL3_RW_AARCH64 | SCR_EL3_HCE_EN |\
+			SCR_EL3_SMD_DIS | SCR_EL3_RES1 |\
+			SCR_EL3_NS_EN)
+	msr	scr_el3, \tmp
 
 	/* Return to the EL2_SP2 mode from EL3 */
-	mov	\xreg1, sp
-	msr	sp_el2, \xreg1		/* Migrate SP */
-	mrs	\xreg1, vbar_el3
-	msr	vbar_el2, \xreg1	/* Migrate VBAR */
-	mov	\xreg1, #0x3c9
-	msr	spsr_el3, \xreg1	/* EL2_SP2 | D | A | I | F */
-	msr	elr_el3, lr
+	ldr	\tmp, =(SPSR_EL_DEBUG_MASK | SPSR_EL_SERR_MASK |\
+			SPSR_EL_IRQ_MASK | SPSR_EL_FIQ_MASK |\
+			SPSR_EL_M_AARCH64 | SPSR_EL_M_EL2H)
+	msr	spsr_el3, \tmp
+	msr	elr_el3, \ep
+	eret
+
+1:
+	/*
+	 * The next lower exception level is AArch32, 32bit EL2 | HCE |
+	 * SMD | RES1 (Bits[5:4]) | Non-secure EL0/EL1.
+	 */
+	ldr	\tmp, =(SCR_EL3_RW_AARCH32 | SCR_EL3_HCE_EN |\
+			SCR_EL3_SMD_DIS | SCR_EL3_RES1 |\
+			SCR_EL3_NS_EN)
+	msr	scr_el3, \tmp
+
+	/* Return to AArch32 Hypervisor mode */
+	ldr     \tmp, =(SPSR_EL_END_LE | SPSR_EL_ASYN_MASK |\
+			SPSR_EL_IRQ_MASK | SPSR_EL_FIQ_MASK |\
+			SPSR_EL_T_A32 | SPSR_EL_M_AARCH32 |\
+			SPSR_EL_M_HYP)
+	msr	spsr_el3, \tmp
+	msr     elr_el3, \ep
 	eret
 .endm
 
-.macro armv8_switch_to_el1_m, xreg1, xreg2
+/*
+ * Switch from EL2 to EL1 for ARMv8
+ * @ep:     kernel entry point
+ * @flag:   The execution state flag for lower exception
+ *          level, ES_TO_AARCH64 or ES_TO_AARCH32
+ * @tmp:    temporary register
+ *
+ * For loading 32-bit OS, x1 is machine nr and x2 is ftaddr.
+ * For loading 64-bit OS, x0 is physical address to the FDT blob.
+ * They will be passed to the guest.
+ */
+.macro armv8_switch_to_el1_m, ep, flag, tmp
 	/* Initialize Generic Timers */
-	mrs	\xreg1, cnthctl_el2
-	orr	\xreg1, \xreg1, #0x3	/* Enable EL1 access to timers */
-	msr	cnthctl_el2, \xreg1
+	mrs	\tmp, cnthctl_el2
+	/* Enable EL1 access to timers */
+	orr	\tmp, \tmp, #(CNTHCTL_EL2_EL1PCEN_EN |\
+		CNTHCTL_EL2_EL1PCTEN_EN)
+	msr	cnthctl_el2, \tmp
 	msr	cntvoff_el2, xzr
 
 	/* Initilize MPID/MPIDR registers */
-	mrs	\xreg1, midr_el1
-	mrs	\xreg2, mpidr_el1
-	msr	vpidr_el2, \xreg1
-	msr	vmpidr_el2, \xreg2
+	mrs	\tmp, midr_el1
+	msr	vpidr_el2, \tmp
+	mrs	\tmp, mpidr_el1
+	msr	vmpidr_el2, \tmp
 
 	/* Disable coprocessor traps */
-	mov	\xreg1, #0x33ff
-	msr	cptr_el2, \xreg1	/* Disable coprocessor traps to EL2 */
+	mov	\tmp, #CPTR_EL2_RES1
+	msr	cptr_el2, \tmp		/* Disable coprocessor traps to EL2 */
 	msr	hstr_el2, xzr		/* Disable coprocessor traps to EL2 */
-	mov	\xreg1, #3 << 20
-	msr	cpacr_el1, \xreg1	/* Enable FP/SIMD at EL1 */
-
-	/* Initialize HCR_EL2 */
-	mov	\xreg1, #(1 << 31)		/* 64bit EL1 */
-	orr	\xreg1, \xreg1, #(1 << 29)	/* Disable HVC */
-	msr	hcr_el2, \xreg1
+	mov	\tmp, #CPACR_EL1_FPEN_EN
+	msr	cpacr_el1, \tmp		/* Enable FP/SIMD at EL1 */
 
 	/* SCTLR_EL1 initialization
 	 *
@@ -199,18 +257,50 @@
 	 * UCI,EE,EOE,WXN,nTWE,nTWI,UCT,DZE,I,UMA,SED,ITD,
 	 * CP15BEN,SA0,SA,C,A,M to 0
 	 */
-	mov	\xreg1, #0x0800
-	movk	\xreg1, #0x30d0, lsl #16
-	msr	sctlr_el1, \xreg1
+	ldr	\tmp, =(SCTLR_EL1_RES1 | SCTLR_EL1_UCI_DIS |\
+			SCTLR_EL1_EE_LE | SCTLR_EL1_WXN_DIS |\
+			SCTLR_EL1_NTWE_DIS | SCTLR_EL1_NTWI_DIS |\
+			SCTLR_EL1_UCT_DIS | SCTLR_EL1_DZE_DIS |\
+			SCTLR_EL1_ICACHE_DIS | SCTLR_EL1_UMA_DIS |\
+			SCTLR_EL1_SED_EN | SCTLR_EL1_ITD_EN |\
+			SCTLR_EL1_CP15BEN_DIS | SCTLR_EL1_SA0_DIS |\
+			SCTLR_EL1_SA_DIS | SCTLR_EL1_DCACHE_DIS |\
+			SCTLR_EL1_ALIGN_DIS | SCTLR_EL1_MMU_DIS)
+	msr	sctlr_el1, \tmp
+
+	mov	\tmp, sp
+	msr	sp_el1, \tmp		/* Migrate SP */
+	mrs	\tmp, vbar_el2
+	msr	vbar_el1, \tmp		/* Migrate VBAR */
+
+	/* Check switch to AArch64 EL1 or AArch32 Supervisor mode */
+	cmp	\flag, #ES_TO_AARCH32
+	b.eq	1f
+
+	/* Initialize HCR_EL2 */
+	ldr	\tmp, =(HCR_EL2_RW_AARCH64 | HCR_EL2_HCD_DIS)
+	msr	hcr_el2, \tmp
 
 	/* Return to the EL1_SP1 mode from EL2 */
-	mov	\xreg1, sp
-	msr	sp_el1, \xreg1		/* Migrate SP */
-	mrs	\xreg1, vbar_el2
-	msr	vbar_el1, \xreg1	/* Migrate VBAR */
-	mov	\xreg1, #0x3c5
-	msr	spsr_el2, \xreg1	/* EL1_SP1 | D | A | I | F */
-	msr	elr_el2, lr
+	ldr	\tmp, =(SPSR_EL_DEBUG_MASK | SPSR_EL_SERR_MASK |\
+			SPSR_EL_IRQ_MASK | SPSR_EL_FIQ_MASK |\
+			SPSR_EL_M_AARCH64 | SPSR_EL_M_EL1H)
+	msr	spsr_el2, \tmp
+	msr     elr_el2, \ep
+	eret
+
+1:
+	/* Initialize HCR_EL2 */
+	ldr	\tmp, =(HCR_EL2_RW_AARCH32 | HCR_EL2_HCD_DIS)
+	msr	hcr_el2, \tmp
+
+	/* Return to AArch32 Supervisor mode from EL2 */
+	ldr	\tmp, =(SPSR_EL_END_LE | SPSR_EL_ASYN_MASK |\
+			SPSR_EL_IRQ_MASK | SPSR_EL_FIQ_MASK |\
+			SPSR_EL_T_A32 | SPSR_EL_M_AARCH32 |\
+			SPSR_EL_M_SVC)
+	msr     spsr_el2, \tmp
+	msr     elr_el2, \ep
 	eret
 .endm
 
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 574a0e7..287ff5c 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -18,6 +18,95 @@
 #define CR_WXN		(1 << 19)	/* Write Permision Imply XN	*/
 #define CR_EE		(1 << 25)	/* Exception (Big) Endian	*/
 
+#define ES_TO_AARCH64		1
+#define ES_TO_AARCH32		0
+
+/*
+ * SCR_EL3 bits definitions
+ */
+#define SCR_EL3_RW_AARCH64	(1 << 10) /* Next lower level is AArch64     */
+#define SCR_EL3_RW_AARCH32	(0 << 10) /* Lower lowers level are AArch32  */
+#define SCR_EL3_HCE_EN		(1 << 8)  /* Hypervisor Call enable          */
+#define SCR_EL3_SMD_DIS		(1 << 7)  /* Secure Monitor Call disable     */
+#define SCR_EL3_RES1		(3 << 4)  /* Reserved, RES1                  */
+#define SCR_EL3_NS_EN		(1 << 0)  /* EL0 and EL1 in Non-scure state  */
+
+/*
+ * SPSR_EL3/SPSR_EL2 bits definitions
+ */
+#define SPSR_EL_END_LE		(0 << 9)  /* Exception Little-endian          */
+#define SPSR_EL_DEBUG_MASK	(1 << 9)  /* Debug exception masked           */
+#define SPSR_EL_ASYN_MASK	(1 << 8)  /* Asynchronous data abort masked   */
+#define SPSR_EL_SERR_MASK	(1 << 8)  /* System Error exception masked    */
+#define SPSR_EL_IRQ_MASK	(1 << 7)  /* IRQ exception masked             */
+#define SPSR_EL_FIQ_MASK	(1 << 6)  /* FIQ exception masked             */
+#define SPSR_EL_T_A32		(0 << 5)  /* AArch32 instruction set A32      */
+#define SPSR_EL_M_AARCH64	(0 << 4)  /* Exception taken from AArch64     */
+#define SPSR_EL_M_AARCH32	(1 << 4)  /* Exception taken from AArch32     */
+#define SPSR_EL_M_SVC		(0x3)     /* Exception taken from SVC mode    */
+#define SPSR_EL_M_HYP		(0xa)     /* Exception taken from HYP mode    */
+#define SPSR_EL_M_EL1H		(5)       /* Exception taken from EL1h mode   */
+#define SPSR_EL_M_EL2H		(9)       /* Exception taken from EL2h mode   */
+
+/*
+ * CPTR_EL2 bits definitions
+ */
+#define CPTR_EL2_RES1		(3 << 12 | 0x3ff)           /* Reserved, RES1 */
+
+/*
+ * SCTLR_EL2 bits definitions
+ */
+#define SCTLR_EL2_RES1		(3 << 28 | 3 << 22 | 1 << 18 | 1 << 16 |\
+				 1 << 11 | 3 << 4)	    /* Reserved, RES1 */
+#define SCTLR_EL2_EE_LE		(0 << 25) /* Exception Little-endian          */
+#define SCTLR_EL2_WXN_DIS	(0 << 19) /* Write permission is not XN       */
+#define SCTLR_EL2_ICACHE_DIS	(0 << 12) /* Instruction cache disabled       */
+#define SCTLR_EL2_SA_DIS	(0 << 3)  /* Stack Alignment Check disabled   */
+#define SCTLR_EL2_DCACHE_DIS	(0 << 2)  /* Data cache disabled              */
+#define SCTLR_EL2_ALIGN_DIS	(0 << 1)  /* Alignment check disabled         */
+#define SCTLR_EL2_MMU_DIS	(0)       /* MMU disabled                     */
+
+/*
+ * CNTHCTL_EL2 bits definitions
+ */
+#define CNTHCTL_EL2_EL1PCEN_EN	(1 << 1)  /* Physical timer regs accessible   */
+#define CNTHCTL_EL2_EL1PCTEN_EN	(1 << 0)  /* Physical counter accessible      */
+
+/*
+ * HCR_EL2 bits definitions
+ */
+#define HCR_EL2_RW_AARCH64	(1 << 31) /* EL1 is AArch64                   */
+#define HCR_EL2_RW_AARCH32	(0 << 31) /* Lower levels are AArch32         */
+#define HCR_EL2_HCD_DIS		(1 << 29) /* Hypervisor Call disabled         */
+
+/*
+ * CPACR_EL1 bits definitions
+ */
+#define CPACR_EL1_FPEN_EN	(3 << 20) /* SIMD and FP instruction enabled  */
+
+/*
+ * SCTLR_EL1 bits definitions
+ */
+#define SCTLR_EL1_RES1		(3 << 28 | 3 << 22 | 1 << 20 |\
+				 1 << 11) /* Reserved, RES1                   */
+#define SCTLR_EL1_UCI_DIS	(0 << 26) /* Cache instruction disabled       */
+#define SCTLR_EL1_EE_LE		(0 << 25) /* Exception Little-endian          */
+#define SCTLR_EL1_WXN_DIS	(0 << 19) /* Write permission is not XN       */
+#define SCTLR_EL1_NTWE_DIS	(0 << 18) /* WFE instruction disabled         */
+#define SCTLR_EL1_NTWI_DIS	(0 << 16) /* WFI instruction disabled         */
+#define SCTLR_EL1_UCT_DIS	(0 << 15) /* CTR_EL0 access disabled          */
+#define SCTLR_EL1_DZE_DIS	(0 << 14) /* DC ZVA instruction disabled      */
+#define SCTLR_EL1_ICACHE_DIS	(0 << 12) /* Instruction cache disabled       */
+#define SCTLR_EL1_UMA_DIS	(0 << 9)  /* User Mask Access disabled        */
+#define SCTLR_EL1_SED_EN	(0 << 8)  /* SETEND instruction enabled       */
+#define SCTLR_EL1_ITD_EN	(0 << 7)  /* IT instruction enabled           */
+#define SCTLR_EL1_CP15BEN_DIS	(0 << 5)  /* CP15 barrier operation disabled  */
+#define SCTLR_EL1_SA0_DIS	(0 << 4)  /* Stack Alignment EL0 disabled     */
+#define SCTLR_EL1_SA_DIS	(0 << 3)  /* Stack Alignment EL1 disabled     */
+#define SCTLR_EL1_DCACHE_DIS	(0 << 2)  /* Data cache disabled              */
+#define SCTLR_EL1_ALIGN_DIS	(0 << 1)  /* Alignment check disabled         */
+#define SCTLR_EL1_MMU_DIS	(0)       /* MMU disabled                     */
+
 #ifndef __ASSEMBLY__
 
 u64 get_page_table_size(void);
@@ -98,8 +187,34 @@
 int __asm_invalidate_l3_icache(void);
 void __asm_switch_ttbr(u64 new_ttbr);
 
-void armv8_switch_to_el2(void);
-void armv8_switch_to_el1(void);
+/*
+ * Switch from EL3 to EL2 for ARMv8
+ *
+ * @args:        For loading 64-bit OS, fdt address.
+ *               For loading 32-bit OS, zero.
+ * @mach_nr:     For loading 64-bit OS, zero.
+ *               For loading 32-bit OS, machine nr
+ * @fdt_addr:    For loading 64-bit OS, zero.
+ *               For loading 32-bit OS, fdt address.
+ * @entry_point: kernel entry point
+ * @es_flag:     execution state flag, ES_TO_AARCH64 or ES_TO_AARCH32
+ */
+void armv8_switch_to_el2(u64 args, u64 mach_nr, u64 fdt_addr,
+			 u64 entry_point, u64 es_flag);
+/*
+ * Switch from EL2 to EL1 for ARMv8
+ *
+ * @args:        For loading 64-bit OS, fdt address.
+ *               For loading 32-bit OS, zero.
+ * @mach_nr:     For loading 64-bit OS, zero.
+ *               For loading 32-bit OS, machine nr
+ * @fdt_addr:    For loading 64-bit OS, zero.
+ *               For loading 32-bit OS, fdt address.
+ * @entry_point: kernel entry point
+ * @es_flag:     execution state flag, ES_TO_AARCH64 or ES_TO_AARCH32
+ */
+void armv8_switch_to_el1(u64 args, u64 mach_nr, u64 fdt_addr,
+			 u64 entry_point, u64 es_flag);
 void gic_init(void);
 void gic_send_sgi(unsigned long sgino);
 void wait_for_wakeup(void);