[boot-wrapper PATCH v3 8/8] aarch64: Introduce EL2 boot code for Armv8-R AArch64

[Jaxson Han]

The Armv8-R AArch64 profile does not support the EL3 exception level.
The Armv8-R AArch64 profile allows for an (optional) VMSAv8-64 MMU
at EL1, which allows to run off-the-shelf Linux. However EL2 only
supports a PMSA, which is not supported by Linux, so we need to drop
into EL1 before entering the kernel.

We add a new err_invalid_arch symbol as a dead loop. If we detect the
current Armv8-R aarch64 only supports with PMSA, meaning we cannot boot
Linux anymore, then we jump to err_invalid_arch.

During Armv8-R aarch64 init, to make sure nothing unexpected traps into
EL2, we auto-detect and config FIEN and EnSCXT in HCR_EL2.

The boot sequence is:
If CurrentEL == EL3, then goto EL3 initialisation and drop to lower EL
  before entering the kernel.
If CurrentEL == EL2 && id_aa64mmfr0_el1.MSA == 0xf (Armv8-R aarch64),
  if id_aa64mmfr0_el1.MSA_frac == 0x2,
    then goto Armv8-R AArch64 initialisation and drop to EL1 before
    entering the kernel.
  else, which means VMSA unsupported and cannot boot Linux,
    goto err_invalid_arch (dead loop).
Else, no initialisation and keep the current EL before entering the
  kernel.

Signed-off-by: Jaxson Han <jaxson.han at arm.com>
---
 arch/aarch64/boot.S            | 92 +++++++++++++++++++++++++++++++++-
 arch/aarch64/include/asm/cpu.h |  2 +
 2 files changed, 92 insertions(+), 2 deletions(-)

diff --git a/arch/aarch64/boot.S b/arch/aarch64/boot.S
index 14fd9cf..461e927 100644
--- a/arch/aarch64/boot.S
+++ b/arch/aarch64/boot.S
@@ -25,16 +25,24 @@ _start:
 	 * Boot sequence
 	 * If CurrentEL == EL3, then goto EL3 initialisation and drop to
 	 *   lower EL before entering the kernel.
+	 * If CurrentEL == EL2 && id_aa64mmfr0_el1.MSA == 0xf, then
+	 *   If id_aa64mmfr0_el1.MSA_frac == 0x2, then goto
+	 *     Armv8-R AArch64 initialisation and drop to EL1 before
+	 *     entering the kernel.
+	 *   Else, which means VMSA unsupported and cannot boot Linux,
+	 *     goto err_invalid_arch (dead loop).
 	 * Else, no initialisation and keep the current EL before
 	 *   entering the kernel.
 	 */
 	mrs	x0, CurrentEL
-	cmp	x0, #CURRENTEL_EL3
-	beq	el3_init
+	cmp	x0, #CURRENTEL_EL2
+	bgt	el3_init
+	beq	el2_init
 
 	/*
 	 * We stay in the current EL for entering the kernel
 	 */
+keep_el:
 	mov	w0, #1
 	ldr	x1, =flag_keep_el
 	str	w0, [x1]
@@ -127,6 +135,85 @@ el3_init:
 	str	w0, [x1]
 	b	el_max_init
 
+	/*
+	 * EL2 Armv8-R AArch64 initialisation
+	 */
+el2_init:
+	/* Detect Armv8-R AArch64 */
+	mrs	x1, id_aa64mmfr0_el1
+	/*
+	 * Check MSA, bits [51:48]:
+	 * 0xf means Armv8-R AArch64.
+	 * If not 0xf, proceed in Armv8-A EL2.
+	 */
+	ubfx	x0, x1, #48, #4			// MSA
+	cmp	x0, 0xf
+	bne	keep_el
+	/*
+	 * Check MSA_frac, bits [55:52]:
+	 * 0x2 means EL1&0 translation regime also supports VMSAv8-64.
+	 */
+	ubfx	x0, x1, #52, #4			// MSA_frac
+	cmp	x0, 0x2
+	/*
+	 * If not 0x2, no VMSA, so cannot boot Linux and dead loop.
+	 * Also, since the architecture guarantees that those CPUID
+	 * fields never lose features when the value in a field
+	 * increases, we use blt to cover it.
+	*/
+	blt	err_invalid_arch
+
+	mrs	x0, midr_el1
+	msr	vpidr_el2, x0
+
+	mrs	x0, mpidr_el1
+	msr	vmpidr_el2, x0
+
+	mov	x0, #(1 << 31)			// VTCR_MSA: VMSAv8-64 support
+	msr	vtcr_el2, x0
+
+	/* Init HCR_EL2 */
+	mov	x0, #(1 << 31)			// RES1: Armv8-R aarch64 only
+
+	mrs	x1, id_aa64pfr0_el1
+	ubfx	x2, x1, #56, 4			// ID_AA64PFR0_EL1.CSV2
+	cmp	x2, 0x2
+	b.lt	1f
+	/*
+	 * Disable trap when accessing SCTXNUM_EL0 or SCTXNUM_EL1
+	 * if FEAT_CSV2.
+	 */
+	orr	x0, x0, #(1 << 53)		// HCR_EL2.EnSCXT
+
+1:	ubfx	x2, x1, #28, 4			// ID_AA64PFR0_EL1.RAS
+	cmp	x2, 0x2
+	b.lt	1f
+	/* Disable trap when accessing ERXPFGCDN_EL1 if FEAT_RASv1p1. */
+	orr	x0, x0, #(1 << 47)		// HCR_EL2.FIEN
+
+	/* Enable pointer authentication if present */
+1:	mrs	x1, id_aa64isar1_el1
+	/*
+	 * If ID_AA64ISAR1_EL1.{GPI, GPA, API, APA} == {0000, 0000, 0000, 0000}
+	 *   then HCR_EL2.APK and HCR_EL2.API are RES 0.
+	 * Else
+	 *   set HCR_EL2.APK and HCR_EL2.API.
+	 */
+	ldr	x2, =(((0xff) << 24) | (0xff << 4))
+	and	x1, x1, x2
+	cbz	x1, 1f
+
+	orr	x0, x0, #(1 << 40)		// HCR_EL2.APK
+	orr	x0, x0, #(1 << 41)		// HCR_EL2.API
+
+1:	msr	hcr_el2, x0
+	isb
+
+	mov	w0, #SPSR_KERNEL_EL1
+	ldr	x1, =spsr_to_elx
+	str	w0, [x1]
+	// fall through
+
 el_max_init:
 	ldr	x0, =CNTFRQ
 	msr	cntfrq_el0, x0
@@ -136,6 +223,7 @@ el_max_init:
 	b	start_el_max
 
 err_invalid_id:
+err_invalid_arch:
 	b	.
 
 	/*
diff --git a/arch/aarch64/include/asm/cpu.h b/arch/aarch64/include/asm/cpu.h
index 3c1ba4b..2b3a0a4 100644
--- a/arch/aarch64/include/asm/cpu.h
+++ b/arch/aarch64/include/asm/cpu.h
@@ -25,6 +25,7 @@
 #define SPSR_I			(1 << 7)	/* IRQ masked */
 #define SPSR_F			(1 << 6)	/* FIQ masked */
 #define SPSR_T			(1 << 5)	/* Thumb */
+#define SPSR_EL1H		(5 << 0)	/* EL1 Handler mode */
 #define SPSR_EL2H		(9 << 0)	/* EL2 Handler mode */
 #define SPSR_HYP		(0x1a << 0)	/* M[3:0] = hyp, M[4] = AArch32 */
 
@@ -43,6 +44,7 @@
 #else
 #define SCTLR_EL1_RESET		SCTLR_EL1_RES1
 #define SPSR_KERNEL		(SPSR_A | SPSR_D | SPSR_I | SPSR_F | SPSR_EL2H)
+#define SPSR_KERNEL_EL1		(SPSR_A | SPSR_D | SPSR_I | SPSR_F | SPSR_EL1H)
 #endif
 
 #ifndef __ASSEMBLY__
-- 
2.25.1