head_64.s

linux-2.6.15.6

	bl	.__mmu_off
	b	.__after_prom_start

_STATIC(__boot_from_prom)
	/* Save parameters */
	mr	r31,r3
	mr	r30,r4
	mr	r29,r5
	mr	r28,r6
	mr	r27,r7

	/* Make sure we are running in 64 bits mode */
	bl	.enable_64b_mode

	/* put a relocation offset into r3 */
	bl	.reloc_offset

	LOADADDR(r2,__toc_start)
	addi	r2,r2,0x4000
	addi	r2,r2,0x4000

	/* Relocate the TOC from a virt addr to a real addr */
	add	r2,r2,r3

	/* Restore parameters */
	mr	r3,r31
	mr	r4,r30
	mr	r5,r29
	mr	r6,r28
	mr	r7,r27

	/* Do all of the interaction with OF client interface */
	bl	.prom_init
	/* We never return */
	trap

/*
 * At this point, r3 contains the physical address we are running at,
 * returned by prom_init()
 */
_STATIC(__after_prom_start)

/*
 * We need to run with __start at physical address 0.
 * This will leave some code in the first 256B of
 * real memory, which are reserved for software use.
 * The remainder of the first page is loaded with the fixed
 * interrupt vectors.  The next two pages are filled with
 * unknown exception placeholders.
 *
 * Note: This process overwrites the OF exception vectors.
 *	r26 == relocation offset
 *	r27 == KERNELBASE
 */
	bl	.reloc_offset
	mr	r26,r3
	SET_REG_TO_CONST(r27,KERNELBASE)

	li	r3,0			/* target addr */

	// XXX FIXME: Use phys returned by OF (r30)
	add	r4,r27,r26 		/* source addr			 */
					/* current address of _start	 */
					/*   i.e. where we are running	 */
					/*	the source addr		 */

	LOADADDR(r5,copy_to_here)	/* # bytes of memory to copy	 */
	sub	r5,r5,r27

	li	r6,0x100		/* Start offset, the first 0x100 */
					/* bytes were copied earlier.	 */

	bl	.copy_and_flush		/* copy the first n bytes	 */
					/* this includes the code being	 */
					/* executed here.		 */

	LOADADDR(r0, 4f)		/* Jump to the copy of this code */
	mtctr	r0			/* that we just made/relocated	 */
	bctr

4:	LOADADDR(r5,klimit)
	add	r5,r5,r26
	ld	r5,0(r5)		/* get the value of klimit */
	sub	r5,r5,r27
	bl	.copy_and_flush		/* copy the rest */
	b	.start_here_multiplatform

#endif /* CONFIG_PPC_MULTIPLATFORM */

/*
 * Copy routine used to copy the kernel to start at physical address 0
 * and flush and invalidate the caches as needed.
 * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
 * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
 *
 * Note: this routine *only* clobbers r0, r6 and lr
 */
_GLOBAL(copy_and_flush)
	addi	r5,r5,-8
	addi	r6,r6,-8
4:	li	r0,16			/* Use the least common		*/
					/* denominator cache line	*/
					/* size.  This results in	*/
					/* extra cache line flushes	*/
					/* but operation is correct.	*/
					/* Can't get cache line size	*/
					/* from NACA as it is being	*/
					/* moved too.			*/

	mtctr	r0			/* put # words/line in ctr	*/
3:	addi	r6,r6,8			/* copy a cache line		*/
	ldx	r0,r6,r4
	stdx	r0,r6,r3
	bdnz	3b
	dcbst	r6,r3			/* write it to memory		*/
	sync
	icbi	r6,r3			/* flush the icache line	*/
	cmpld	0,r6,r5
	blt	4b
	sync
	addi	r5,r5,8
	addi	r6,r6,8
	blr

.align 8
copy_to_here:

#ifdef CONFIG_SMP
#ifdef CONFIG_PPC_PMAC
/*
 * On PowerMac, secondary processors starts from the reset vector, which
 * is temporarily turned into a call to one of the functions below.
 */
	.section ".text";
	.align 2 ;

	.globl	__secondary_start_pmac_0
__secondary_start_pmac_0:
	/* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */
	li	r24,0
	b	1f
	li	r24,1
	b	1f
	li	r24,2
	b	1f
	li	r24,3
1:
	
_GLOBAL(pmac_secondary_start)
	/* turn on 64-bit mode */
	bl	.enable_64b_mode
	isync

	/* Copy some CPU settings from CPU 0 */
	bl	.__restore_cpu_setup

	/* pSeries do that early though I don't think we really need it */
	mfmsr	r3
	ori	r3,r3,MSR_RI
	mtmsrd	r3			/* RI on */

	/* Set up a paca value for this processor. */
	LOADADDR(r4, paca) 		 /* Get base vaddr of paca array	*/
	mulli	r13,r24,PACA_SIZE	 /* Calculate vaddr of right paca */
	add	r13,r13,r4		/* for this processor.		*/
	mtspr	SPRN_SPRG3,r13		 /* Save vaddr of paca in SPRG3	*/

	/* Create a temp kernel stack for use before relocation is on.	*/
	ld	r1,PACAEMERGSP(r13)
	subi	r1,r1,STACK_FRAME_OVERHEAD

	b	.__secondary_start

#endif /* CONFIG_PPC_PMAC */

/*
 * This function is called after the master CPU has released the
 * secondary processors.  The execution environment is relocation off.
 * The paca for this processor has the following fields initialized at
 * this point:
 *   1. Processor number
 *   2. Segment table pointer (virtual address)
 * On entry the following are set:
 *   r1	= stack pointer.  vaddr for iSeries, raddr (temp stack) for pSeries
 *   r24   = cpu# (in Linux terms)
 *   r13   = paca virtual address
 *   SPRG3 = paca virtual address
 */
_GLOBAL(__secondary_start)
	/* Set thread priority to MEDIUM */
	HMT_MEDIUM

	/* Load TOC */
	ld	r2,PACATOC(r13)

	/* Do early setup for that CPU (stab, slb, hash table pointer) */
	bl	.early_setup_secondary

	/* Initialize the kernel stack.  Just a repeat for iSeries.	 */
	LOADADDR(r3,current_set)
	sldi	r28,r24,3		/* get current_set[cpu#]	 */
	ldx	r1,r3,r28
	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
	std	r1,PACAKSAVE(r13)

	/* Clear backchain so we get nice backtraces */
	li	r7,0
	mtlr	r7

	/* enable MMU and jump to start_secondary */
	LOADADDR(r3,.start_secondary_prolog)
	SET_REG_TO_CONST(r4, MSR_KERNEL)
#ifdef DO_SOFT_DISABLE
	ori	r4,r4,MSR_EE
#endif
	mtspr	SPRN_SRR0,r3
	mtspr	SPRN_SRR1,r4
	rfid
	b	.	/* prevent speculative execution */

/* 
 * Running with relocation on at this point.  All we want to do is
 * zero the stack back-chain pointer before going into C code.
 */
_GLOBAL(start_secondary_prolog)
	li	r3,0
	std	r3,0(r1)		/* Zero the stack frame pointer	*/
	bl	.start_secondary
	b	.
#endif

/*
 * This subroutine clobbers r11 and r12
 */
_GLOBAL(enable_64b_mode)
	mfmsr	r11			/* grab the current MSR */
	li	r12,1
	rldicr	r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
	or	r11,r11,r12
	li	r12,1
	rldicr	r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
	or	r11,r11,r12
	mtmsrd	r11
	isync
	blr

#ifdef CONFIG_PPC_MULTIPLATFORM
/*
 * This is where the main kernel code starts.
 */
_STATIC(start_here_multiplatform)
	/* get a new offset, now that the kernel has moved. */
	bl	.reloc_offset
	mr	r26,r3

	/* Clear out the BSS. It may have been done in prom_init,
	 * already but that's irrelevant since prom_init will soon
	 * be detached from the kernel completely. Besides, we need
	 * to clear it now for kexec-style entry.
	 */
	LOADADDR(r11,__bss_stop)
	LOADADDR(r8,__bss_start)
	sub	r11,r11,r8		/* bss size			*/
	addi	r11,r11,7		/* round up to an even double word */
	rldicl. r11,r11,61,3		/* shift right by 3		*/
	beq	4f
	addi	r8,r8,-8
	li	r0,0
	mtctr	r11			/* zero this many doublewords	*/
3:	stdu	r0,8(r8)
	bdnz	3b
4:

	mfmsr	r6
	ori	r6,r6,MSR_RI
	mtmsrd	r6			/* RI on */

#ifdef CONFIG_HMT
	/* Start up the second thread on cpu 0 */
	mfspr	r3,SPRN_PVR
	srwi	r3,r3,16
	cmpwi	r3,0x34			/* Pulsar  */
	beq	90f
	cmpwi	r3,0x36			/* Icestar */
	beq	90f
	cmpwi	r3,0x37			/* SStar   */
	beq	90f
	b	91f			/* HMT not supported */
90:	li	r3,0
	bl	.hmt_start_secondary
91:
#endif

	/* The following gets the stack and TOC set up with the regs */
	/* pointing to the real addr of the kernel stack.  This is   */
	/* all done to support the C function call below which sets  */
	/* up the htab.  This is done because we have relocated the  */
	/* kernel but are still running in real mode. */

	LOADADDR(r3,init_thread_union)
	add	r3,r3,r26

	/* set up a stack pointer (physical address) */
	addi	r1,r3,THREAD_SIZE
	li	r0,0
	stdu	r0,-STACK_FRAME_OVERHEAD(r1)

	/* set up the TOC (physical address) */
	LOADADDR(r2,__toc_start)
	addi	r2,r2,0x4000
	addi	r2,r2,0x4000
	add	r2,r2,r26

	LOADADDR(r3,cpu_specs)
	add	r3,r3,r26
	LOADADDR(r4,cur_cpu_spec)
	add	r4,r4,r26
	mr	r5,r26
	bl	.identify_cpu

	/* Save some low level config HIDs of CPU0 to be copied to
	 * other CPUs later on, or used for suspend/resume
	 */
	bl	.__save_cpu_setup
	sync

	/* Setup a valid physical PACA pointer in SPRG3 for early_setup
	 * note that boot_cpuid can always be 0 nowadays since there is
	 * nowhere it can be initialized differently before we reach this
	 * code
	 */
	LOADADDR(r27, boot_cpuid)
	add	r27,r27,r26
	lwz	r27,0(r27)

	LOADADDR(r24, paca) 		/* Get base vaddr of paca array	 */
	mulli	r13,r27,PACA_SIZE	/* Calculate vaddr of right paca */
	add	r13,r13,r24		/* for this processor.		 */
	add	r13,r13,r26		/* convert to physical addr	 */
	mtspr	SPRN_SPRG3,r13		/* PPPBBB: Temp... -Peter */
	
	/* Do very early kernel initializations, including initial hash table,
	 * stab and slb setup before we turn on relocation.	*/

	/* Restore parameters passed from prom_init/kexec */
	mr	r3,r31
 	bl	.early_setup

	LOADADDR(r3,.start_here_common)
	SET_REG_TO_CONST(r4, MSR_KERNEL)
	mtspr	SPRN_SRR0,r3
	mtspr	SPRN_SRR1,r4
	rfid
	b	.	/* prevent speculative execution */
#endif /* CONFIG_PPC_MULTIPLATFORM */
	
	/* This is where all platforms converge execution */
_STATIC(start_here_common)
	/* relocation is on at this point */

	/* The following code sets up the SP and TOC now that we are */
	/* running with translation enabled. */

	LOADADDR(r3,init_thread_union)

	/* set up the stack */
	addi	r1,r3,THREAD_SIZE
	li	r0,0
	stdu	r0,-STACK_FRAME_OVERHEAD(r1)

	/* Apply the CPUs-specific fixups (nop out sections not relevant
	 * to this CPU
	 */
	li	r3,0
	bl	.do_cpu_ftr_fixups

	LOADADDR(r26, boot_cpuid)
	lwz	r26,0(r26)

	LOADADDR(r24, paca) 		/* Get base vaddr of paca array  */
	mulli	r13,r26,PACA_SIZE	/* Calculate vaddr of right paca */
	add	r13,r13,r24		/* for this processor.		 */
	mtspr	SPRN_SPRG3,r13

	/* ptr to current */
	LOADADDR(r4,init_task)
	std	r4,PACACURRENT(r13)

	/* Load the TOC */
	ld	r2,PACATOC(r13)
	std	r1,PACAKSAVE(r13)

	bl	.setup_system

	/* Load up the kernel context */
5:
#ifdef DO_SOFT_DISABLE
	li	r5,0
	stb	r5,PACAPROCENABLED(r13)	/* Soft Disabled */
	mfmsr	r5
	ori	r5,r5,MSR_EE		/* Hard Enabled */
	mtmsrd	r5
#endif

	bl .start_kernel

_GLOBAL(hmt_init)
#ifdef CONFIG_HMT
	LOADADDR(r5, hmt_thread_data)
	mfspr	r7,SPRN_PVR
	srwi	r7,r7,16
	cmpwi	r7,0x34			/* Pulsar  */
	beq	90f
	cmpwi	r7,0x36			/* Icestar */
	beq	91f
	cmpwi	r7,0x37			/* SStar   */
	beq	91f
	b	101f
90:	mfspr	r6,SPRN_PIR
	andi.	r6,r6,0x1f
	b	92f
91:	mfspr	r6,SPRN_PIR
	andi.	r6,r6,0x3ff
92:	sldi	r4,r24,3
	stwx	r6,r5,r4
	bl	.hmt_start_secondary
	b	101f

__hmt_secondary_hold:
	LOADADDR(r5, hmt_thread_data)
	clrldi	r5,r5,4
	li	r7,0
	mfspr	r6,SPRN_PIR
	mfspr	r8,SPRN_PVR
	srwi	r8,r8,16
	cmpwi	r8,0x34
	bne	93f
	andi.	r6,r6,0x1f
	b	103f
93:	andi.	r6,r6,0x3f

103:	lwzx	r8,r5,r7
	cmpw	r8,r6
	beq	104f
	addi	r7,r7,8
	b	103b

104:	addi	r7,r7,4
	lwzx	r9,r5,r7
	mr	r24,r9
101:
#endif
	mr	r3,r24
	b	.pSeries_secondary_smp_init

#ifdef CONFIG_HMT
_GLOBAL(hmt_start_secondary)
	LOADADDR(r4,__hmt_secondary_hold)
	clrldi	r4,r4,4
	mtspr	SPRN_NIADORM, r4
	mfspr	r4, SPRN_MSRDORM
	li	r5, -65
	and	r4, r4, r5
	mtspr	SPRN_MSRDORM, r4
	lis	r4,0xffef
	ori	r4,r4,0x7403
	mtspr	SPRN_TSC, r4
	li	r4,0x1f4
	mtspr	SPRN_TST, r4
	mfspr	r4, SPRN_HID0
	ori	r4, r4, 0x1
	mtspr	SPRN_HID0, r4
	mfspr	r4, SPRN_CTRLF
	oris	r4, r4, 0x40
	mtspr	SPRN_CTRLT, r4
	blr
#endif

/*
 * We put a few things here that have to be page-aligned.
 * This stuff goes at the beginning of the bss, which is page-aligned.
 */
	.section ".bss"

	.align	PAGE_SHIFT

	.globl	empty_zero_page
empty_zero_page:
	.space	PAGE_SIZE

	.globl	swapper_pg_dir
swapper_pg_dir:
	.space	PAGE_SIZE

/*
 * This space gets a copy of optional info passed to us by the bootstrap
 * Used to pass parameters into the kernel like root=/dev/sda1, etc.
 */
	.globl	cmd_line
cmd_line:
	.space	COMMAND_LINE_SIZE