head.s

linux-2.6.15.6

		mov	r12, lr
		bl	__setup_mmu
		mov	r0, #0
		mcr	p15, 0, r0, c7, c10, 4	@ drain write buffer
		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
		orr	r0, r0, #0x0030
		bl	__common_cache_on
		mov	r0, #0
		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
		mov	pc, r12

__arm6_cache_on:
		mov	r12, lr
		bl	__setup_mmu
		mov	r0, #0
		mcr	p15, 0, r0, c7, c0, 0	@ invalidate whole cache v3
		mcr	p15, 0, r0, c5, c0, 0	@ invalidate whole TLB v3
		mov	r0, #0x30
		bl	__common_cache_on
		mov	r0, #0
		mcr	p15, 0, r0, c5, c0, 0	@ invalidate whole TLB v3
		mov	pc, r12

__common_cache_on:
#ifndef DEBUG
		orr	r0, r0, #0x000d		@ Write buffer, mmu
#endif
		mov	r1, #-1
		mcr	p15, 0, r3, c2, c0, 0	@ load page table pointer
		mcr	p15, 0, r1, c3, c0, 0	@ load domain access control
		mcr	p15, 0, r0, c1, c0, 0	@ load control register
		mov	pc, lr

/*
 * All code following this line is relocatable.  It is relocated by
 * the above code to the end of the decompressed kernel image and
 * executed there.  During this time, we have no stacks.
 *
 * r0     = decompressed kernel length
 * r1-r3  = unused
 * r4     = kernel execution address
 * r5     = decompressed kernel start
 * r6     = processor ID
 * r7     = architecture ID
 * r8-r14 = unused
 */
		.align	5
reloc_start:	add	r8, r5, r0
		debug_reloc_start
		mov	r1, r4
1:
		.rept	4
		ldmia	r5!, {r0, r2, r3, r9 - r13}	@ relocate kernel
		stmia	r1!, {r0, r2, r3, r9 - r13}
		.endr

		cmp	r5, r8
		blo	1b
		debug_reloc_end

call_kernel:	bl	cache_clean_flush
		bl	cache_off
		mov	r0, #0
		mov	r1, r7			@ restore architecture number
		mov	pc, r4			@ call kernel

/*
 * Here follow the relocatable cache support functions for the
 * various processors.  This is a generic hook for locating an
 * entry and jumping to an instruction at the specified offset
 * from the start of the block.  Please note this is all position
 * independent code.
 *
 *  r1  = corrupted
 *  r2  = corrupted
 *  r3  = block offset
 *  r6  = corrupted
 *  r12 = corrupted
 */

call_cache_fn:	adr	r12, proc_types
		mrc	p15, 0, r6, c0, c0	@ get processor ID
1:		ldr	r1, [r12, #0]		@ get value
		ldr	r2, [r12, #4]		@ get mask
		eor	r1, r1, r6		@ (real ^ match)
		tst	r1, r2			@       & mask
		addeq	pc, r12, r3		@ call cache function
		add	r12, r12, #4*5
		b	1b

/*
 * Table for cache operations.  This is basically:
 *   - CPU ID match
 *   - CPU ID mask
 *   - 'cache on' method instruction
 *   - 'cache off' method instruction
 *   - 'cache flush' method instruction
 *
 * We match an entry using: ((real_id ^ match) & mask) == 0
 *
 * Writethrough caches generally only need 'on' and 'off'
 * methods.  Writeback caches _must_ have the flush method
 * defined.
 */
		.type	proc_types,#object
proc_types:
		.word	0x41560600		@ ARM6/610
		.word	0xffffffe0
		b	__arm6_cache_off	@ works, but slow
		b	__arm6_cache_off
		mov	pc, lr
@		b	__arm6_cache_on		@ untested
@		b	__arm6_cache_off
@		b	__armv3_cache_flush

		.word	0x00000000		@ old ARM ID
		.word	0x0000f000
		mov	pc, lr
		mov	pc, lr
		mov	pc, lr

		.word	0x41007000		@ ARM7/710
		.word	0xfff8fe00
		b	__arm7_cache_off
		b	__arm7_cache_off
		mov	pc, lr

		.word	0x41807200		@ ARM720T (writethrough)
		.word	0xffffff00
		b	__armv4_cache_on
		b	__armv4_cache_off
		mov	pc, lr

		.word	0x00007000		@ ARM7 IDs
		.word	0x0000f000
		mov	pc, lr
		mov	pc, lr
		mov	pc, lr

		@ Everything from here on will be the new ID system.

		.word	0x4401a100		@ sa110 / sa1100
		.word	0xffffffe0
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv4_cache_flush

		.word	0x6901b110		@ sa1110
		.word	0xfffffff0
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv4_cache_flush

		@ These match on the architecture ID

		.word	0x00020000		@ ARMv4T
		.word	0x000f0000
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv4_cache_flush

		.word	0x00050000		@ ARMv5TE
		.word	0x000f0000
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv4_cache_flush

		.word	0x00060000		@ ARMv5TEJ
		.word	0x000f0000
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv4_cache_flush

		.word	0x00070000		@ ARMv6
		.word	0x000f0000
		b	__armv4_cache_on
		b	__armv4_cache_off
		b	__armv6_cache_flush

		.word	0			@ unrecognised type
		.word	0
		mov	pc, lr
		mov	pc, lr
		mov	pc, lr

		.size	proc_types, . - proc_types

/*
 * Turn off the Cache and MMU.  ARMv3 does not support
 * reading the control register, but ARMv4 does.
 *
 * On entry,  r6 = processor ID
 * On exit,   r0, r1, r2, r3, r12 corrupted
 * This routine must preserve: r4, r6, r7
 */
		.align	5
cache_off:	mov	r3, #12			@ cache_off function
		b	call_cache_fn

__armv4_cache_off:
		mrc	p15, 0, r0, c1, c0
		bic	r0, r0, #0x000d
		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
		mov	r0, #0
		mcr	p15, 0, r0, c7, c7	@ invalidate whole cache v4
		mcr	p15, 0, r0, c8, c7	@ invalidate whole TLB v4
		mov	pc, lr

__arm6_cache_off:
		mov	r0, #0x00000030		@ ARM6 control reg.
		b	__armv3_cache_off

__arm7_cache_off:
		mov	r0, #0x00000070		@ ARM7 control reg.
		b	__armv3_cache_off

__armv3_cache_off:
		mcr	p15, 0, r0, c1, c0, 0	@ turn MMU and cache off
		mov	r0, #0
		mcr	p15, 0, r0, c7, c0, 0	@ invalidate whole cache v3
		mcr	p15, 0, r0, c5, c0, 0	@ invalidate whole TLB v3
		mov	pc, lr

/*
 * Clean and flush the cache to maintain consistency.
 *
 * On entry,
 *  r6 = processor ID
 * On exit,
 *  r1, r2, r3, r11, r12 corrupted
 * This routine must preserve:
 *  r0, r4, r5, r6, r7
 */
		.align	5
cache_clean_flush:
		mov	r3, #16
		b	call_cache_fn

__armv6_cache_flush:
		mov	r1, #0
		mcr	p15, 0, r1, c7, c14, 0	@ clean+invalidate D
		mcr	p15, 0, r1, c7, c5, 0	@ invalidate I+BTB
		mcr	p15, 0, r1, c7, c15, 0	@ clean+invalidate unified
		mcr	p15, 0, r1, c7, c10, 4	@ drain WB
		mov	pc, lr

__armv4_cache_flush:
		mov	r2, #64*1024		@ default: 32K dcache size (*2)
		mov	r11, #32		@ default: 32 byte line size
		mrc	p15, 0, r3, c0, c0, 1	@ read cache type
		teq	r3, r6			@ cache ID register present?
		beq	no_cache_id
		mov	r1, r3, lsr #18
		and	r1, r1, #7
		mov	r2, #1024
		mov	r2, r2, lsl r1		@ base dcache size *2
		tst	r3, #1 << 14		@ test M bit
		addne	r2, r2, r2, lsr #1	@ +1/2 size if M == 1
		mov	r3, r3, lsr #12
		and	r3, r3, #3
		mov	r11, #8
		mov	r11, r11, lsl r3	@ cache line size in bytes
no_cache_id:
		bic	r1, pc, #63		@ align to longest cache line
		add	r2, r1, r2
1:		ldr	r3, [r1], r11		@ s/w flush D cache
		teq	r1, r2
		bne	1b

		mcr	p15, 0, r1, c7, c5, 0	@ flush I cache
		mcr	p15, 0, r1, c7, c6, 0	@ flush D cache
		mcr	p15, 0, r1, c7, c10, 4	@ drain WB
		mov	pc, lr

__armv3_cache_flush:
		mov	r1, #0
		mcr	p15, 0, r0, c7, c0, 0	@ invalidate whole cache v3
		mov	pc, lr

/*
 * Various debugging routines for printing hex characters and
 * memory, which again must be relocatable.
 */
#ifdef DEBUG
		.type	phexbuf,#object
phexbuf:	.space	12
		.size	phexbuf, . - phexbuf

phex:		adr	r3, phexbuf
		mov	r2, #0
		strb	r2, [r3, r1]
1:		subs	r1, r1, #1
		movmi	r0, r3
		bmi	puts
		and	r2, r0, #15
		mov	r0, r0, lsr #4
		cmp	r2, #10
		addge	r2, r2, #7
		add	r2, r2, #'0'
		strb	r2, [r3, r1]
		b	1b

puts:		loadsp	r3
1:		ldrb	r2, [r0], #1
		teq	r2, #0
		moveq	pc, lr
2:		writeb	r2, r3
		mov	r1, #0x00020000
3:		subs	r1, r1, #1
		bne	3b
		teq	r2, #'\n'
		moveq	r2, #'\r'
		beq	2b
		teq	r0, #0
		bne	1b
		mov	pc, lr
putc:
		mov	r2, r0
		mov	r0, #0
		loadsp	r3
		b	2b

memdump:	mov	r12, r0
		mov	r10, lr
		mov	r11, #0
2:		mov	r0, r11, lsl #2
		add	r0, r0, r12
		mov	r1, #8
		bl	phex
		mov	r0, #':'
		bl	putc
1:		mov	r0, #' '
		bl	putc
		ldr	r0, [r12, r11, lsl #2]
		mov	r1, #8
		bl	phex
		and	r0, r11, #7
		teq	r0, #3
		moveq	r0, #' '
		bleq	putc
		and	r0, r11, #7
		add	r11, r11, #1
		teq	r0, #7
		bne	1b
		mov	r0, #'\n'
		bl	putc
		cmp	r11, #64
		blt	2b
		mov	pc, r10
#endif

reloc_end:

		.align
		.section ".stack", "w"
user_stack:	.space	4096