/* SPDX-License-Identifier: GPL-2.0-only */
/*
 *  linux/arch/arm/kernel/head.S
 *
 *  Copyright (C) 1994-2002 Russell King
 *  Copyright (c) 2003 ARM Limited
 *  All Rights Reserved
 *
 *  Kernel startup code for all 32-bit CPUs
 */
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/pgtable.h>

#include <asm/assembler.h>
#include <asm/cp15.h>
#include <asm/domain.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
#include <asm/page.h>
#include <asm/thread_info.h>

#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
#include CONFIG_DEBUG_LL_INCLUDE
#endif
/*
 * swapper_pg_dir is the virtual address of the initial page table.
 * We place the page tables 16K below KERNEL_RAM_VADDR.  Therefore, we must
 * make sure that KERNEL_RAM_VADDR is correctly set.  Currently, we expect
 * the least significant 16 bits to be 0x8000, but we could probably
 * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000.
 */
#define KERNEL_RAM_VADDR	(KERNEL_OFFSET + TEXT_OFFSET)
#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
#error KERNEL_RAM_VADDR must start at 0xXXXX8000
#endif

#ifdef CONFIG_ARM_LPAE
	/* LPAE requires an additional page for the PGD */
#define PG_DIR_SIZE	0x5000
#define PMD_ENTRY_ORDER	3	/* PMD entry size is 2^PMD_ENTRY_ORDER */
#else
#define PG_DIR_SIZE	0x4000
#define PMD_ENTRY_ORDER	2
#endif

	.globl	swapper_pg_dir
	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE

	/*
	 * This needs to be assigned at runtime when the linker symbols are
	 * resolved. These are unsigned 64bit really, but in this assembly code
	 * We store them as 32bit.
	 */
	.pushsection .data
	.align	2
	.globl	kernel_sec_start
	.globl	kernel_sec_end
kernel_sec_start:
	.long	0
	.long	0
kernel_sec_end:
	.long	0
	.long	0
	.popsection

	.macro	pgtbl, rd, phys
	add	\rd, \phys, #TEXT_OFFSET
	sub	\rd, \rd, #PG_DIR_SIZE
	.endm

/*
 * Kernel startup entry point.
 * ---------------------------
 *
 * This is normally called from the decompressor code.  The requirements
 * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
 * r1 = machine nr, r2 = atags or dtb pointer.
 *
 * This code is mostly position independent, so if you link the kernel at
 * 0xc0008000, you call this at __pa(0xc0008000).
 *
 * See linux/arch/arm/tools/mach-types for the complete list of machine
 * numbers for r1.
 *
 * We're trying to keep crap to a minimum; DO NOT add any machine specific
 * crap here - that's what the boot loader (or in extreme, well justified
 * circumstances, zImage) is for.
 */
	.arm

	__HEAD
ENTRY(stext)
 ARM_BE8(setend	be )			@ ensure we are in BE8 mode

 THUMB(	badr	r9, 1f		)	@ Kernel is always entered in ARM.
 THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
 THUMB(	.thumb			)	@ switch to Thumb now.
 THUMB(1:			)

#ifdef CONFIG_ARM_VIRT_EXT
	bl	__hyp_stub_install
#endif
	@ ensure svc mode and all interrupts masked
	safe_svcmode_maskall r9

	mrc	p15, 0, r9, c0, c0		@ get processor id
	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
	movs	r10, r5				@ invalid processor (r5=0)?
 THUMB( it	eq )		@ force fixup-able long branch encoding
	beq	__error_p			@ yes, error 'p'

#ifdef CONFIG_ARM_LPAE
	mrc	p15, 0, r3, c0, c1, 4		@ read ID_MMFR0
	and	r3, r3, #0xf			@ extract VMSA support
	cmp	r3, #5				@ long-descriptor translation table format?
 THUMB( it	lo )				@ force fixup-able long branch encoding
	blo	__error_lpae			@ only classic page table format
#endif

#ifndef CONFIG_XIP_KERNEL
	adr_l	r8, _text			@ __pa(_text)
	sub	r8, r8, #TEXT_OFFSET		@ PHYS_OFFSET
#else
	ldr	r8, =PLAT_PHYS_OFFSET		@ always constant in this case
#endif

	/*
	 * r1 = machine no, r2 = atags or dtb,
	 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
	 */
	bl	__vet_atags
#ifdef CONFIG_SMP_ON_UP
	bl	__fixup_smp
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
	bl	__fixup_pv_table
#endif
	bl	__create_page_tables

	/*
	 * The following calls CPU specific code in a position independent
	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
	 * xxx_proc_info structure selected by __lookup_processor_type
	 * above.
	 *
	 * The processor init function will be called with:
	 *  r1 - machine type
	 *  r2 - boot data (atags/dt) pointer
	 *  r4 - translation table base (low word)
	 *  r5 - translation table base (high word, if LPAE)
	 *  r8 - translation table base 1 (pfn if LPAE)
	 *  r9 - cpuid
	 *  r13 - virtual address for __enable_mmu -> __turn_mmu_on
	 *
	 * On return, the CPU will be ready for the MMU to be turned on,
	 * r0 will hold the CPU control register value, r1, r2, r4, and
	 * r9 will be preserved.  r5 will also be preserved if LPAE.
	 */
	ldr	r13, =__mmap_switched		@ address to jump to after
						@ mmu has been enabled
	badr	lr, 1f				@ return (PIC) address
#ifdef CONFIG_ARM_LPAE
	mov	r5, #0				@ high TTBR0
	mov	r8, r4, lsr #12			@ TTBR1 is swapper_pg_dir pfn
#else
	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
#endif
	ldr	r12, [r10, #PROCINFO_INITFUNC]
	add	r12, r12, r10
	ret	r12
1:	b	__enable_mmu
ENDPROC(stext)
	.ltorg

/*
 * Setup the initial page tables.  We only setup the barest
 * amount which are required to get the kernel running, which
 * generally means mapping in the kernel code.
 *
 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
 *
 * Returns:
 *  r0, r3, r5-r7 corrupted
 *  r4 = physical page table address
 */
__create_page_tables:
	pgtbl	r4, r8				@ page table address

	/*
	 * Clear the swapper page table
	 */
	mov	r0, r4
	mov	r3, #0
	add	r6, r0, #PG_DIR_SIZE
1:	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
	teq	r0, r6
	bne	1b

#ifdef CONFIG_ARM_LPAE
	/*
	 * Build the PGD table (first level) to point to the PMD table. A PGD
	 * entry is 64-bit wide.
	 */
	mov	r0, r4
	add	r3, r4, #0x1000			@ first PMD table address
	orr	r3, r3, #3			@ PGD block type
	mov	r6, #4				@ PTRS_PER_PGD
	mov	r7, #1 << (55 - 32)		@ L_PGD_SWAPPER
1:
#ifdef CONFIG_CPU_ENDIAN_BE8
	str	r7, [r0], #4			@ set top PGD entry bits
	str	r3, [r0], #4			@ set bottom PGD entry bits
#else
	str	r3, [r0], #4			@ set bottom PGD entry bits
	str	r7, [r0], #4			@ set top PGD entry bits
#endif
	add	r3, r3, #0x1000			@ next PMD table
	subs	r6, r6, #1
	bne	1b

	add	r4, r4, #0x1000			@ point to the PMD tables
#ifdef CONFIG_CPU_ENDIAN_BE8
	add	r4, r4, #4			@ we only write the bottom word
#endif
#endif

	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags

	/*
	 * Create identity mapping to cater for __enable_mmu.
	 * This identity mapping will be removed by paging_init().
	 */
	adr_l	r5, __turn_mmu_on		@ _pa(__turn_mmu_on)
	adr_l	r6, __turn_mmu_on_end		@ _pa(__turn_mmu_on_end)
	mov	r5, r5, lsr #SECTION_SHIFT
	mov	r6, r6, lsr #SECTION_SHIFT

1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
	str	r3, [r4, r5, lsl #PMD_ENTRY_ORDER]	@ identity mapping
	cmp	r5, r6
	addlo	r5, r5, #1			@ next section
	blo	1b

	/*
	 * The main matter: map in the kernel using section mappings, and
	 * set two variables to indicate the physical start and end of the
	 * kernel.
	 */
	add	r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	ldr	r6, =(_end - 1)
	adr_l	r5, kernel_sec_start		@ _pa(kernel_sec_start)
#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
	str	r8, [r5, #4]			@ Save physical start of kernel (BE)
#else
	str	r8, [r5]			@ Save physical start of kernel (LE)
#endif
	orr	r3, r8, r7			@ Add the MMU flags
	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER)
1:	str	r3, [r0], #1 << PMD_ENTRY_ORDER
	add	r3, r3, #1 << SECTION_SHIFT
	cmp	r0, r6
	bls	1b
	eor	r3, r3, r7			@ Remove the MMU flags
	adr_l	r5, kernel_sec_end		@ _pa(kernel_sec_end)
#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
	str	r3, [r5, #4]			@ Save physical end of kernel (BE)
#else
	str	r3, [r5]			@ Save physical end of kernel (LE)
#endif

#ifdef CONFIG_XIP_KERNEL
	/*
	 * Map the kernel image separately as it is not located in RAM.
	 */
#define XIP_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
	mov	r3, pc
	mov	r3, r3, lsr #SECTION_SHIFT
	orr	r3, r7, r3, lsl #SECTION_SHIFT
	add	r0, r4,  #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	str	r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ENTRY_ORDER]!
	ldr	r6, =(_edata_loc - 1)
	add	r0, r0, #1 << PMD_ENTRY_ORDER
	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER)
1:	cmp	r0, r6
	add	r3, r3, #1 << SECTION_SHIFT
	strls	r3, [r0], #1 << PMD_ENTRY_ORDER
	bls	1b
#endif

	/*
	 * Then map boot params address in r2 if specified.
	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
	 */
	mov	r0, r2, lsr #SECTION_SHIFT
	cmp	r2, #0
	ldrne	r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	addne	r3, r3, r4
	orrne	r6, r7, r0, lsl #SECTION_SHIFT
	strne	r6, [r3], #1 << PMD_ENTRY_ORDER
	addne	r6, r6, #1 << SECTION_SHIFT
	strne	r6, [r3]

#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8)
	sub	r4, r4, #4			@ Fixup page table pointer
						@ for 64-bit descriptors
#endif

#ifdef CONFIG_DEBUG_LL
#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
	/*
	 * Map in IO space for serial debugging.
	 * This allows debug messages to be output
	 * via a serial console before paging_init.
	 */
	addruart r7, r3, r0

	mov	r3, r3, lsr #SECTION_SHIFT
	mov	r3, r3, lsl #PMD_ENTRY_ORDER

	add	r0, r4, r3
	mov	r3, r7, lsr #SECTION_SHIFT
	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
	orr	r3, r7, r3, lsl #SECTION_SHIFT
#ifdef CONFIG_ARM_LPAE
	mov	r7, #1 << (54 - 32)		@ XN
#ifdef CONFIG_CPU_ENDIAN_BE8
	str	r7, [r0], #4
	str	r3, [r0], #4
#else
	str	r3, [r0], #4
	str	r7, [r0], #4
#endif
#else
	orr	r3, r3, #PMD_SECT_XN
	str	r3, [r0], #4
#endif

#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
	/* we don't need any serial debugging mappings */
	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
#endif

#if defined(CONFIG_ARCH_NETWINDER)
	/*
	 * If we're using the NetWinder or CATS, we also need to map
	 * in the 16550-type serial port for the debug messages
	 */
	add	r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	orr	r3, r7, #0x7c000000
	str	r3, [r0]
#endif
#ifdef CONFIG_ARCH_RPC
	/*
	 * Map in screen at 0x02000000 & SCREEN2_BASE
	 * Similar reasons here - for debug.  This is
	 * only for Acorn RiscPC architectures.
	 */
	add	r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	orr	r3, r7, #0x02000000
	str	r3, [r0]
	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
	str	r3, [r0]
#endif
#endif
#ifdef CONFIG_ARM_LPAE
	sub	r4, r4, #0x1000		@ point to the PGD table
#endif
	ret	lr
ENDPROC(__create_page_tables)
	.ltorg

#if defined(CONFIG_SMP)
	.text
	.arm
ENTRY(secondary_startup_arm)
 THUMB(	badr	r9, 1f		)	@ Kernel is entered in ARM.
 THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
 THUMB(	.thumb			)	@ switch to Thumb now.
 THUMB(1:			)
ENTRY(secondary_startup)
	/*
	 * Common entry point for secondary CPUs.
	 *
	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
	 * the processor type - there is no need to check the machine type
	 * as it has already been validated by the primary processor.
	 */

 ARM_BE8(setend	be)				@ ensure we are in BE8 mode

#ifdef CONFIG_ARM_VIRT_EXT
	bl	__hyp_stub_install_secondary
#endif
	safe_svcmode_maskall r9

	mrc	p15, 0, r9, c0, c0		@ get processor id
	bl	__lookup_processor_type
	movs	r10, r5				@ invalid processor?
	moveq	r0, #'p'			@ yes, error 'p'
 THUMB( it	eq )		@ force fixup-able long branch encoding
	beq	__error_p

	/*
	 * Use the page tables supplied from  __cpu_up.
	 */
	adr_l	r3, secondary_data
	mov_l	r12, __secondary_switched
	ldrd	r4, r5, [r3, #0]		@ get secondary_data.pgdir
ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
	badr	lr, __enable_mmu		@ return address
	mov	r13, r12			@ __secondary_switched address
	ldr	r12, [r10, #PROCINFO_INITFUNC]
	add	r12, r12, r10			@ initialise processor
						@ (return control reg)
	ret	r12
ENDPROC(secondary_startup)
ENDPROC(secondary_startup_arm)

ENTRY(__secondary_switched)
#if defined(CONFIG_VMAP_STACK) && !defined(CONFIG_ARM_LPAE)
	@ Before using the vmap'ed stack, we have to switch to swapper_pg_dir
	@ as the ID map does not cover the vmalloc region.
	mrc	p15, 0, ip, c2, c0, 1	@ read TTBR1
	mcr	p15, 0, ip, c2, c0, 0	@ set TTBR0
	instr_sync
#endif
	adr_l	r7, secondary_data + 12		@ get secondary_data.stack
	ldr	sp, [r7]
	ldr	r0, [r7, #4]			@ get secondary_data.task
	mov	fp, #0
	b	secondary_start_kernel
ENDPROC(__secondary_switched)

#endif /* defined(CONFIG_SMP) */


/*
 * Setup common bits before finally enabling the MMU.  Essentially
 * this is just loading the page table pointer and domain access
 * registers.  All these registers need to be preserved by the
 * processor setup function (or set in the case of r0)
 *
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r4  = TTBR pointer (low word)
 *  r5  = TTBR pointer (high word if LPAE)
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 */
__enable_mmu:
#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
	orr	r0, r0, #CR_A
#else
	bic	r0, r0, #CR_A
#endif
#ifdef CONFIG_CPU_DCACHE_DISABLE
	bic	r0, r0, #CR_C
#endif
#ifdef CONFIG_CPU_BPREDICT_DISABLE
	bic	r0, r0, #CR_Z
#endif
#ifdef CONFIG_CPU_ICACHE_DISABLE
	bic	r0, r0, #CR_I
#endif
#ifdef CONFIG_ARM_LPAE
	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
#else
	mov	r5, #DACR_INIT
	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
#endif
	b	__turn_mmu_on
ENDPROC(__enable_mmu)

/*
 * Enable the MMU.  This completely changes the structure of the visible
 * memory space.  You will not be able to trace execution through this.
 * If you have an enquiry about this, *please* check the linux-arm-kernel
 * mailing list archives BEFORE sending another post to the list.
 *
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 *
 * other registers depend on the function called upon completion
 */
	.align	5
	.pushsection	.idmap.text, "ax"
ENTRY(__turn_mmu_on)
	mov	r0, r0
	instr_sync
	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
	instr_sync
	mov	r3, r3
	mov	r3, r13
	ret	r3
__turn_mmu_on_end:
ENDPROC(__turn_mmu_on)
	.popsection


#ifdef CONFIG_SMP_ON_UP
	__HEAD
__fixup_smp:
	and	r3, r9, #0x000f0000	@ architecture version
	teq	r3, #0x000f0000		@ CPU ID supported?
	bne	__fixup_smp_on_up	@ no, assume UP

	bic	r3, r9, #0x00ff0000
	bic	r3, r3, #0x0000000f	@ mask 0xff00fff0
	mov	r4, #0x41000000
	orr	r4, r4, #0x0000b000
	orr	r4, r4, #0x00000020	@ val 0x4100b020
	teq	r3, r4			@ ARM 11MPCore?
	reteq	lr			@ yes, assume SMP

	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
	teq	r0, #0x80000000		@ not part of a uniprocessor system?
	bne    __fixup_smp_on_up	@ no, assume UP

	@ Core indicates it is SMP. Check for Aegis SOC where a single
	@ Cortex-A9 CPU is present but SMP operations fault.
	mov	r4, #0x41000000
	orr	r4, r4, #0x0000c000
	orr	r4, r4, #0x00000090
	teq	r3, r4			@ Check for ARM Cortex-A9
	retne	lr			@ Not ARM Cortex-A9,

	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
	@ below address check will need to be #ifdef'd or equivalent
	@ for the Aegis platform.
	mrc	p15, 4, r0, c15, c0	@ get SCU base address
	teq	r0, #0x0		@ '0' on actual UP A9 hardware
	beq	__fixup_smp_on_up	@ So its an A9 UP
	ldr	r0, [r0, #4]		@ read SCU Config
ARM_BE8(rev	r0, r0)			@ byteswap if big endian
	and	r0, r0, #0x3		@ number of CPUs
	teq	r0, #0x0		@ is 1?
	retne	lr

__fixup_smp_on_up:
	adr_l	r4, __smpalt_begin
	adr_l	r5, __smpalt_end
	b	__do_fixup_smp_on_up
ENDPROC(__fixup_smp)

	.pushsection .data
	.align	2
	.globl	smp_on_up
smp_on_up:
	ALT_SMP(.long	1)
	ALT_UP(.long	0)
	.popsection
#endif

	.text
__do_fixup_smp_on_up:
	cmp	r4, r5
	reths	lr
	ldmia	r4, {r0, r6}
 ARM(	str	r6, [r0, r4]	)
 THUMB(	add	r0, r0, r4	)
	add	r4, r4, #8
#ifdef __ARMEB__
 THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
#endif
 THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
 THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r0.
 THUMB(	strh	r6, [r0]	)
	b	__do_fixup_smp_on_up
ENDPROC(__do_fixup_smp_on_up)

ENTRY(fixup_smp)
	stmfd	sp!, {r4 - r6, lr}
	mov	r4, r0
	add	r5, r0, r1
	bl	__do_fixup_smp_on_up
	ldmfd	sp!, {r4 - r6, pc}
ENDPROC(fixup_smp)

#include "head-common.S"