start.s

uboot for at91rm9200dk

/* Description:	 Input 8 bits */
/*------------------------------------------------------------------------------- */
	.globl	in8
in8:
	lbz	r3,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out8 */
/* Description:	 Output 8 bits */
/*------------------------------------------------------------------------------- */
	.globl	out8
out8:
	stb	r4,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out16 */
/* Description:	 Output 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	out16
out16:
	sth	r4,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out16r */
/* Description:	 Byte reverse and output 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	out16r
out16r:
	sthbrx	r4,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out32 */
/* Description:	 Output 32 bits */
/*------------------------------------------------------------------------------- */
	.globl	out32
out32:
	stw	r4,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out32r */
/* Description:	 Byte reverse and output 32 bits */
/*------------------------------------------------------------------------------- */
	.globl	out32r
out32r:
	stwbrx	r4,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in16 */
/* Description:	 Input 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	in16
in16:
	lhz	r3,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in16r */
/* Description:	 Input 16 bits and byte reverse */
/*------------------------------------------------------------------------------- */
	.globl	in16r
in16r:
	lhbrx	r3,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in32 */
/* Description:	 Input 32 bits */
/*------------------------------------------------------------------------------- */
	.globl	in32
in32:
	lwz	3,0x0000(3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in32r */
/* Description:	 Input 32 bits and byte reverse */
/*------------------------------------------------------------------------------- */
	.globl	in32r
in32r:
	lwbrx	r3,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcDcbf */
/* Description:	 Data Cache block flush */
/* Input:	 r3 = effective address */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcDcbf
ppcDcbf:
	dcbf	r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcDcbi */
/* Description:	 Data Cache block Invalidate */
/* Input:	 r3 = effective address */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcDcbi
ppcDcbi:
	dcbi	r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcSync */
/* Description:	 Processor Synchronize */
/* Input:	 none. */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcSync
ppcSync:
	sync
	blr

/*------------------------------------------------------------------------------*/

/*
 * void relocate_code (addr_sp, gd, addr_moni)
 *
 * This "function" does not return, instead it continues in RAM
 * after relocating the monitor code.
 *
 * r3 = dest
 * r4 = src
 * r5 = length in bytes
 * r6 = cachelinesize
 */
	.globl	relocate_code
relocate_code:
	mr	r1,  r3		/* Set new stack pointer		*/
	mr	r9,  r4		/* Save copy of Init Data pointer	*/
	mr	r10, r5		/* Save copy of Destination Address	*/

	mr	r3,  r5				/* Destination Address	*/
	lis	r4, CFG_MONITOR_BASE@h		/* Source      Address	*/
	ori	r4, r4, CFG_MONITOR_BASE@l
	lwz	r5, GOT(__init_end)
	sub	r5, r5, r4
	li	r6, CFG_CACHELINE_SIZE		/* Cache Line Size	*/

	/*
	 * Fix GOT pointer:
	 *
	 * New GOT-PTR = (old GOT-PTR - CFG_MONITOR_BASE) + Destination Address
	 *
	 * Offset:
	 */
	sub	r15, r10, r4

	/* First our own GOT */
	add	r14, r14, r15
	/* the the one used by the C code */
	add	r30, r30, r15

	/*
	 * Now relocate code
	 */

	cmplw	cr1,r3,r4
	addi	r0,r5,3
	srwi.	r0,r0,2
	beq	cr1,4f		/* In place copy is not necessary	*/
	beq	7f		/* Protect against 0 count		*/
	mtctr	r0
	bge	cr1,2f

	la	r8,-4(r4)
	la	r7,-4(r3)
1:	lwzu	r0,4(r8)
	stwu	r0,4(r7)
	bdnz	1b
	b	4f

2:	slwi	r0,r0,2
	add	r8,r4,r0
	add	r7,r3,r0
3:	lwzu	r0,-4(r8)
	stwu	r0,-4(r7)
	bdnz	3b

/*
 * Now flush the cache: note that we must start from a cache aligned
 * address. Otherwise we might miss one cache line.
 */
4:	cmpwi	r6,0
	add	r5,r3,r5
	beq	7f		/* Always flush prefetch queue in any case */
	subi	r0,r6,1
	andc	r3,r3,r0
	mr	r4,r3
5:	dcbst	0,r4
	add	r4,r4,r6
	cmplw	r4,r5
	blt	5b
	sync			/* Wait for all dcbst to complete on bus */
	mr	r4,r3
6:	icbi	0,r4
	add	r4,r4,r6
	cmplw	r4,r5
	blt	6b
7:	sync			/* Wait for all icbi to complete on bus */
	isync

/*
 * We are done. Do not return, instead branch to second part of board
 * initialization, now running from RAM.
 */

	addi	r0, r10, in_ram - _start + EXC_OFF_SYS_RESET
	mtlr	r0
	blr				/* NEVER RETURNS! */

in_ram:

	/*
	 * Relocation Function, r14 point to got2+0x8000
	 *
	 * Adjust got2 pointers, no need to check for 0, this code
	 * already puts a few entries in the table.
	 */
	li	r0,__got2_entries@sectoff@l
	la	r3,GOT(_GOT2_TABLE_)
	lwz	r11,GOT(_GOT2_TABLE_)
	mtctr	r0
	sub	r11,r3,r11
	addi	r3,r3,-4
1:	lwzu	r0,4(r3)
	add	r0,r0,r11
	stw	r0,0(r3)
	bdnz	1b

	/*
	 * Now adjust the fixups and the pointers to the fixups
	 * in case we need to move ourselves again.
	 */
2:	li	r0,__fixup_entries@sectoff@l
	lwz	r3,GOT(_FIXUP_TABLE_)
	cmpwi	r0,0
	mtctr	r0
	addi	r3,r3,-4
	beq	4f
3:	lwzu	r4,4(r3)
	lwzux	r0,r4,r11
	add	r0,r0,r11
	stw	r10,0(r3)
	stw	r0,0(r4)
	bdnz	3b
4:
clear_bss:
	/*
	 * Now clear BSS segment
	 */
	lwz	r3,GOT(__bss_start)
	lwz	r4,GOT(_end)

	cmplw	0, r3, r4
	beq	6f

	li	r0, 0
5:
	stw	r0, 0(r3)
	addi	r3, r3, 4
	cmplw	0, r3, r4
	bne	5b
6:

	mr	r3, r9		/* Init Data pointer		*/
	mr	r4, r10		/* Destination Address		*/
	bl	board_init_r

	/*
	 * Copy exception vector code to low memory
	 *
	 * r3: dest_addr
	 * r7: source address, r8: end address, r9: target address
	 */
	.globl	trap_init
trap_init:
	lwz	r7, GOT(_start)
	lwz	r8, GOT(_end_of_vectors)

	li	r9, 0x100		/* reset vector always at 0x100 */

	cmplw	0, r7, r8
	bgelr				/* return if r7>=r8 - just in case */

	mflr	r4			/* save link register		*/
1:
	lwz	r0, 0(r7)
	stw	r0, 0(r9)
	addi	r7, r7, 4
	addi	r9, r9, 4
	cmplw	0, r7, r8
	bne	1b

	/*
	 * relocate `hdlr' and `int_return' entries
	 */
	li	r7, .L_MachineCheck - _start + EXC_OFF_SYS_RESET
	li	r8, Alignment - _start + EXC_OFF_SYS_RESET
2:
	bl	trap_reloc
	addi	r7, r7, 0x100		/* next exception vector	*/
	cmplw	0, r7, r8
	blt	2b

	li	r7, .L_Alignment - _start + EXC_OFF_SYS_RESET
	bl	trap_reloc

	li	r7, .L_ProgramCheck - _start + EXC_OFF_SYS_RESET
	bl	trap_reloc

	li	r7, .L_FPUnavailable - _start + EXC_OFF_SYS_RESET
	li	r8, SystemCall - _start + EXC_OFF_SYS_RESET
3:
	bl	trap_reloc
	addi	r7, r7, 0x100		/* next exception vector	*/
	cmplw	0, r7, r8
	blt	3b

	li	r7, .L_SingleStep - _start + EXC_OFF_SYS_RESET
	li	r8, _end_of_vectors - _start + EXC_OFF_SYS_RESET
4:
	bl	trap_reloc
	addi	r7, r7, 0x100		/* next exception vector	*/
	cmplw	0, r7, r8
	blt	4b

	mtlr	r4			/* restore link register	*/
	blr

	/*
	 * Function: relocate entries for one exception vector
	 */
trap_reloc:
	lwz	r0, 0(r7)		/* hdlr ...			*/
	add	r0, r0, r3		/*  ... += dest_addr		*/
	stw	r0, 0(r7)

	lwz	r0, 4(r7)		/* int_return ...		*/
	add	r0, r0, r3		/*  ... += dest_addr		*/
	stw	r0, 4(r7)

	blr


/**************************************************************************/
/* PPC405EP specific stuff                                                */
/**************************************************************************/
#ifdef CONFIG_405EP
ppc405ep_init:
	/*
	!-----------------------------------------------------------------------
	! Check FPGA for PCI internal/external arbitration
	!   If board is set to internal arbitration, update cpc0_pci
	!-----------------------------------------------------------------------
	*/
	addi    r3,0,CPC0_PCI_HOST_CFG_EN
#ifdef CONFIG_BUBINGA405EP
	addis   r5,r0,FPGA_REG1@h      /* set offset for FPGA_REG1 */
	ori     r5,r5,FPGA_REG1@l
	lbz     r5,0x0(r5)              /* read to get PCI arb selection */
	andi.   r6,r5,FPGA_REG1_PCI_INT_ARB  /* using internal arbiter ?*/
	beq     ..pci_cfg_set             /* if not set, then bypass reg write*/
#endif
	ori     r3,r3,CPC0_PCI_ARBIT_EN
..pci_cfg_set:
	mtdcr   CPC0_PCI, r3             /* Enable internal arbiter*/

	/*
	!-----------------------------------------------------------------------
	! Check to see if chip is in bypass mode.
	! If so, write stored CPC0_PLLMR0 and CPC0_PLLMR1 values and perform a
	! CPU reset   Otherwise, skip this step and keep going.
	! Note:  Running BIOS in bypass mode is not supported since PLB speed
	!        will not be fast enough for the SDRAM (min 66MHz)
	!-----------------------------------------------------------------------
	*/
	mfdcr   r5, CPC0_PLLMR1
	rlwinm  r4,r5,1,0x1            /* get system clock source (SSCS) */
	cmpi    cr0,0,r4,0x1

	beq    pll_done                   /* if SSCS =b'1' then PLL has */
					  /* already been set */
					  /* and CPU has been reset */
					  /* so skip to next section */

#ifdef CONFIG_BUBINGA405EP
	/*
	!-----------------------------------------------------------------------
	! Read NVRAM to get value to write in PLLMR.
	! If value has not been correctly saved, write default value
	! Default config values (assuming on-board 33MHz SYS_CLK) are above.
	! See CPU_DEFAULT_200 and CPU_DEFAULT_266 above.
	!
	! WARNING:  This code assumes the first three words in the nvram_t
	!           structure in openbios.h.  Changing the beginning of
	!           the structure will break this code.
	!
	!-----------------------------------------------------------------------
	*/
	addis   r3,0,NVRAM_BASE@h
	addi    r3,r3,NVRAM_BASE@l

	lwz     r4, 0(r3)
	addis   r5,0,NVRVFY1@h
	addi    r5,r5,NVRVFY1@l
	cmp     cr0,0,r4,r5            /* Compare 1st NVRAM Magic number*/
	bne     ..no_pllset
	addi    r3,r3,4
	lwz     r4, 0(r3)
	addis   r5,0,NVRVFY2@h
	addi    r5,r5,NVRVFY2@l
	cmp     cr0,0,r4,r5            /* Compare 2 NVRAM Magic number */
	bne     ..no_pllset
	addi    r3,r3,8                 /* Skip over conf_size */
	lwz     r4, 4(r3)               /* Load PLLMR1 value from NVRAM */
	lwz     r3, 0(r3)               /* Load PLLMR0 value from NVRAM */
	rlwinm  r5,r4,1,0x1             /* get system clock source (SSCS) */
	cmpi     cr0,0,r5,1             /* See if PLL is locked */
	beq     pll_write
..no_pllset:
#endif /* CONFIG_BUBINGA405EP */

	addis   r3,0,PLLMR0_DEFAULT@h       /* PLLMR0 default value */
	ori     r3,r3,PLLMR0_DEFAULT@l     /* */
	addis   r4,0,PLLMR1_DEFAULT@h       /* PLLMR1 default value */
	ori     r4,r4,PLLMR1_DEFAULT@l     /* */

	b       pll_write                 /* Write the CPC0_PLLMR with new value */

pll_done:
	/*
	!-----------------------------------------------------------------------
	! Clear Soft Reset Register
	! This is needed to enable PCI if not booting from serial EPROM
	!-----------------------------------------------------------------------
		*/
	addi    r3, 0, 0x0
	mtdcr   CPC0_SRR, r3

	addis    r3,0,0x0010
	mtctr   r3
pci_wait:
	bdnz    pci_wait

	blr				  /* return to main code */

/*
!-----------------------------------------------------------------------------
! Function:     pll_write
! Description:  Updates the value of the CPC0_PLLMR according to CMOS27E documentation
!               That is:
!                         1.  Pll is first disabled (de-activated by putting in bypass mode)
!                         2.  PLL is reset
!                         3.  Clock dividers are set while PLL is held in reset and bypassed
!                         4.  PLL Reset is cleared
!                         5.  Wait 100us for PLL to lock
!                         6.  A core reset is performed
! Input: r3 = Value to write to CPC0_PLLMR0
! Input: r4 = Value to write to CPC0_PLLMR1
! Output r3 = none
!-----------------------------------------------------------------------------
*/
pll_write:
	mfdcr  r5, CPC0_UCR
	andis. r5,r5,0xFFFF
	ori    r5,r5,0x0101              /* Stop the UART clocks */
	mtdcr  CPC0_UCR,r5               /* Before changing PLL */

	mfdcr  r5, CPC0_PLLMR1
	rlwinm r5,r5,0,0x7FFFFFFF        /* Disable PLL */
	mtdcr   CPC0_PLLMR1,r5
	oris   r5,r5,0x4000              /* Set PLL Reset */
	mtdcr   CPC0_PLLMR1,r5

	mtdcr   CPC0_PLLMR0,r3           /* Set clock dividers */
	rlwinm r5,r4,0,0x3FFFFFFF        /* Reset & Bypass new PLL dividers */
	oris   r5,r5,0x4000              /* Set PLL Reset */
	mtdcr   CPC0_PLLMR1,r5           /* Set clock dividers */
	rlwinm r5,r5,0,0xBFFFFFFF        /* Clear PLL Reset */
	mtdcr   CPC0_PLLMR1,r5

		/*
	! Wait min of 100us for PLL to lock.
	! See CMOS 27E databook for more info.
	! At 200MHz, that means waiting 20,000 instructions
		 */
	addi    r3,0,20000              /* 2000 = 0x4e20 */
	mtctr   r3
pll_wait:
	bdnz    pll_wait

	oris   r5,r5,0x8000             /* Enable PLL */
	mtdcr   CPC0_PLLMR1,r5          /* Engage */

	/*
	 * Reset CPU to guarantee timings are OK
	 * Not sure if this is needed...
	 */
	addis r3,0,0x1000
	mtspr dbcr0,r3               /* This will cause a CPU core reset, and */
				     /* execution will continue from the poweron */
				     /* vector of 0xfffffffc */
#endif /* CONFIG_405EP */